Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.9401. Min Act: -0.1700
Data Index: 7127802 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.9401. Min Act: -0.1700
Data Index: 3003342 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.8776. Min Act: -0.1700
Data Index: 7127805 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.8463. Min Act: -0.1700
Data Index: 7393385 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.7838. Min Act: -0.1700
Data Index: 7738044 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.7526. Min Act: -0.1700
Data Index: 4109133 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.7526. Min Act: -0.1700
Data Index: 7393384 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.7526. Min Act: -0.1700
Data Index: 6699030 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.7526. Min Act: -0.1700
Data Index: 3449428 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 8440336 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 4776699 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 7519324 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 528258 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 2986494 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6901. Min Act: -0.1700
Data Index: 5151002 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6588. Min Act: -0.1700
Data Index: 4266197 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6276. Min Act: -0.1700
Data Index: 6884999 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6588. Min Act: -0.1700
Data Index: 6880368 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6588. Min Act: -0.1700
Data Index: 1055868 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9401. Min Range: -4.9401
Max Act: 4.6588. Min Act: -0.1700
Data Index: 913308 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19