Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.9197. Min Act: -0.1700
Data Index: 2801379 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8885. Min Act: -0.1700
Data Index: 5450897 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8885. Min Act: -0.1700
Data Index: 3544957 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8572. Min Act: -0.1700
Data Index: 6884435 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8572. Min Act: -0.1700
Data Index: 2014587 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8259. Min Act: -0.1700
Data Index: 234900 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8259. Min Act: -0.1700
Data Index: 368869 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.8259. Min Act: -0.1700
Data Index: 1231649 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5146030 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7947. Min Act: -0.1700
Data Index: 4801094 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7947. Min Act: -0.1700
Data Index: 5798104 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7634. Min Act: -0.1700
Data Index: 7876977 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7634. Min Act: -0.1700
Data Index: 245895 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7321. Min Act: -0.1700
Data Index: 4106204 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7634. Min Act: -0.1700
Data Index: 7567225 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7634. Min Act: -0.1700
Data Index: 6603932 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7008. Min Act: -0.1700
Data Index: 4912698 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7008. Min Act: -0.1700
Data Index: 7099987 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.6695. Min Act: -0.1700
Data Index: 4818509 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9197. Min Range: -3.9197
Max Act: 3.7008. Min Act: -0.1700
Data Index: 4351561 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19