Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 935 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0385. Min Range: -5.0385
Max Act: 5.0385. Min Act: -0.1700
Data Index: 191016 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.9135. Min Act: -0.1700
Data Index: 136493 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.9135. Min Act: -0.1700
Data Index: 5580319 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.8510. Min Act: -0.1700
Data Index: 1054949 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.8510. Min Act: -0.1700
Data Index: 6591474 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7885. Min Act: -0.1700
Data Index: 5514983 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7885. Min Act: -0.1700
Data Index: 6052723 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7572. Min Act: -0.1700
Data Index: 8616190 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7572. Min Act: -0.1700
Data Index: 263529 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2209855 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7572. Min Act: -0.1700
Data Index: 3327554 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1119359 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7885. Min Act: -0.1700
Data Index: 3470957 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7885. Min Act: -0.1700
Data Index: 4870735 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.6635. Min Act: -0.1700
Data Index: 4587929 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.6947. Min Act: -0.1700
Data Index: 5943 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7260. Min Act: -0.1700
Data Index: 2355020 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.7260. Min Act: -0.1700
Data Index: 191015 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.6947. Min Act: -0.1700
Data Index: 2684992 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0385. Min Range: -5.0385
Max Act: 4.6947. Min Act: -0.1700
Data Index: 2782622 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19