Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.5067. Min Act: -0.1700
Data Index: 8133135 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.3192. Min Act: -0.1700
Data Index: 2714002 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.2566. Min Act: -0.1700
Data Index: 88007 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.0066. Min Act: -0.1700
Data Index: 3120268 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.9753. Min Act: -0.1700
Data Index: 1774947 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.9441. Min Act: -0.1700
Data Index: 1570562 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.8815. Min Act: -0.1700
Data Index: 3979321 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.9128. Min Act: -0.1700
Data Index: 1978675 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.8815. Min Act: -0.1700
Data Index: 6770264 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.8503. Min Act: -0.1700
Data Index: 1697303 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.8503. Min Act: -0.1700
Data Index: 192102 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7877. Min Act: -0.1700
Data Index: 3174714 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 8757835 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7877. Min Act: -0.1700
Data Index: 4394249 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 3808645 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 6463857 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 6648304 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 1255783 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7877. Min Act: -0.1700
Data Index: 1150700 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5067. Min Range: -4.5067
Max Act: 3.7565. Min Act: -0.1700
Data Index: 2422074 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19