Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.9803. Min Act: -0.1700
Data Index: 8075132 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.9178. Min Act: -0.1700
Data Index: 1709479 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.9178. Min Act: -0.1700
Data Index: 6380945 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.8553. Min Act: -0.1700
Data Index: 2352217 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.7928. Min Act: -0.1700
Data Index: 2139738 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.5115. Min Act: -0.1700
Data Index: 5752211 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.5115. Min Act: -0.1700
Data Index: 8405077 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4803. Min Act: -0.1700
Data Index: 2807801 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4490. Min Act: -0.1700
Data Index: 6982622 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4178. Min Act: -0.1700
Data Index: 1442570 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4178. Min Act: -0.1700
Data Index: 2848467 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4178. Min Act: -0.1700
Data Index: 4287516 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.4178. Min Act: -0.1700
Data Index: 2060888 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3865. Min Act: -0.1700
Data Index: 1864383 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3865. Min Act: -0.1700
Data Index: 1791422 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3865. Min Act: -0.1700
Data Index: 8102860 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3865. Min Act: -0.1700
Data Index: 5824113 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3240. Min Act: -0.1700
Data Index: 5227844 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3553. Min Act: -0.1700
Data Index: 3867209 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9803. Min Range: -6.9803
Max Act: 6.3553. Min Act: -0.1700
Data Index: 3059865 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19