Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.1557. Min Act: -0.1700
Data Index: 999537 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.1557. Min Act: -0.1700
Data Index: 8799163 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.0927. Min Act: -0.1700
Data Index: 6052576 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.0612. Min Act: -0.1700
Data Index: 685790 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.0927. Min Act: -0.1700
Data Index: 5616607 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.0454. Min Act: -0.1700
Data Index: 4606269 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1557. Min Range: -3.1557
Max Act: 3.0138. Min Act: -0.1700
Data Index: 8702547 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9822. Min Act: -0.1700
Data Index: 902097 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9664. Min Act: -0.1700
Data Index: 914882 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9822. Min Act: -0.1700
Data Index: 1451842 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9506. Min Act: -0.1700
Data Index: 601106 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9506. Min Act: -0.1700
Data Index: 5219507 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9347. Min Act: -0.1700
Data Index: 3982197 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9506. Min Act: -0.1700
Data Index: 7880372 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9347. Min Act: -0.1700
Data Index: 7321248 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9347. Min Act: -0.1700
Data Index: 3732877 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9347. Min Act: -0.1700
Data Index: 4851612 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9189. Min Act: -0.1700
Data Index: 7525456 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9189. Min Act: -0.1700
Data Index: 6237799 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1557. Min Range: -3.1557
Max Act: 2.9030. Min Act: -0.1700
Data Index: 6703199 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19