Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.4667. Min Act: -0.1678
Data Index: 2992520 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.4667. Min Act: -0.1700
Data Index: 7658869 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.4667. Min Act: -0.1678
Data Index: 6191658 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1685
Data Index: 4810349 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1677
Data Index: 5465948 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1699
Data Index: 5354651 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1461
Data Index: 4971048 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1694
Data Index: 432280 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1700
Data Index: 1520452 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1695
Data Index: 1476633 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1685
Data Index: 2612688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1700
Data Index: 974527 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.3417. Min Act: -0.1700
Data Index: 8023474 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1697
Data Index: 4227025 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1700
Data Index: 2867908 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1699
Data Index: 3906748 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1700
Data Index: 2001534 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1700
Data Index: 3251831 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1700
Data Index: 3285718 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.4667. Min Range: -18.4667
Max Act: 18.2167. Min Act: -0.1697
Data Index: 5679159 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19