Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1311 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.8189. Min Act: -0.1700
Data Index: 710800 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.8103. Min Act: -0.1700
Data Index: 2375528 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.8017. Min Act: -0.1700
Data Index: 5167907 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.8017. Min Act: -0.1700
Data Index: 4748582 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.8103. Min Act: -0.1700
Data Index: 3805280 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7931. Min Act: -0.1700
Data Index: 2868073 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 4656870 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7759. Min Act: -0.1700
Data Index: 8623297 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 1978100 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 7263115 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7931. Min Act: -0.1700
Data Index: 8301943 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 797552 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 6719051 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7673. Min Act: -0.1700
Data Index: 113127 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7759. Min Act: -0.1700
Data Index: 293279 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7845. Min Act: -0.1700
Data Index: 6496079 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7673. Min Act: -0.1700
Data Index: 6236732 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7586. Min Act: -0.1700
Data Index: 3468649 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7673. Min Act: -0.1700
Data Index: 963335 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8189. Min Range: -1.8189
Max Act: 1.7586. Min Act: -0.1700
Data Index: 7685498 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19