Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2896 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.8072. Min Act: -0.1700
Data Index: 8806975 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.7135. Min Act: -0.1700
Data Index: 5123276 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.6510. Min Act: -0.1700
Data Index: 3712069 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.5885. Min Act: -0.1700
Data Index: 6083328 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.5260. Min Act: -0.1700
Data Index: 2487208 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.4947. Min Act: -0.1700
Data Index: 6119210 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.4947. Min Act: -0.1700
Data Index: 1439631 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.4322. Min Act: -0.1700
Data Index: 4686913 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.4010. Min Act: -0.1700
Data Index: 7919100 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3697. Min Act: -0.1700
Data Index: 2528761 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3385. Min Act: -0.1700
Data Index: 309588 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3385. Min Act: -0.1700
Data Index: 4636737 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3385. Min Act: -0.1700
Data Index: 563200 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3072. Min Act: -0.1700
Data Index: 6718444 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.3072. Min Act: -0.1700
Data Index: 3106125 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.2447. Min Act: -0.1700
Data Index: 4683590 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.2447. Min Act: -0.1700
Data Index: 5726102 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.2135. Min Act: -0.1700
Data Index: 6953256 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.1822. Min Act: -0.1700
Data Index: 3473670 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8072. Min Range: -7.8072
Max Act: 7.1822. Min Act: -0.1700
Data Index: 3754928 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19