Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1714 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.5739. Min Act: -0.1700
Data Index: 5808592 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.5426. Min Act: -0.1700
Data Index: 2596742 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.5426. Min Act: -0.1700
Data Index: 4975274 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.4801. Min Act: -0.1700
Data Index: 474645 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.4176. Min Act: -0.1700
Data Index: 3425411 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3551. Min Act: -0.1700
Data Index: 4352409 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3551. Min Act: -0.1700
Data Index: 5023427 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3864. Min Act: -0.1700
Data Index: 4092276 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3551. Min Act: -0.1700
Data Index: 3905 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3239. Min Act: -0.1700
Data Index: 4219424 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 2268399 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3551. Min Act: -0.1700
Data Index: 6098093 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3239. Min Act: -0.1700
Data Index: 1291695 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3239. Min Act: -0.1700
Data Index: 807136 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 1175204 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.3239. Min Act: -0.1700
Data Index: 4413532 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 5556112 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 3197455 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 5147231 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5739. Min Range: -4.5739
Max Act: 4.2926. Min Act: -0.1700
Data Index: 406467 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19