Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.9523. Min Act: -0.1700
Data Index: 2145399 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.9210. Min Act: -0.1700
Data Index: 6477320 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.8585. Min Act: -0.1700
Data Index: 7668844 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.8272. Min Act: -0.1700
Data Index: 758739 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.7334. Min Act: -0.1700
Data Index: 3008803 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.7334. Min Act: -0.1700
Data Index: 8358327 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.7334. Min Act: -0.1700
Data Index: 3686103 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.7021. Min Act: -0.1700
Data Index: 7252966 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6708. Min Act: -0.1700
Data Index: 7347080 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 5862140 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 1248168 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 7408531 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 6437151 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 2334017 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 4136872 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 7677648 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 3003090 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 5422205 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6395. Min Act: -0.1700
Data Index: 972793 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9523. Min Range: -3.9523
Max Act: 3.6082. Min Act: -0.1700
Data Index: 202525 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19