Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4914 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.7239. Min Act: -0.1700
Data Index: 1900274 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.6301. Min Act: -0.1700
Data Index: 7968461 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5988. Min Act: -0.1700
Data Index: 1990590 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5361. Min Act: -0.1700
Data Index: 5868477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5361. Min Act: -0.1700
Data Index: 4291197 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5361. Min Act: -0.1700
Data Index: 1900288 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5048. Min Act: -0.1700
Data Index: 5113960 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4892. Min Act: -0.1700
Data Index: 4973075 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5048. Min Act: -0.1700
Data Index: 1282698 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.5518. Min Act: -0.1700
Data Index: 3753763 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4892. Min Act: -0.1700
Data Index: 3354679 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4892. Min Act: -0.1700
Data Index: 7477902 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4578. Min Act: -0.1700
Data Index: 6405627 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4578. Min Act: -0.1700
Data Index: 6782080 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4265. Min Act: -0.1700
Data Index: 7223338 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.3951. Min Act: -0.1700
Data Index: 5459283 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4108. Min Act: -0.1700
Data Index: 4940329 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.3951. Min Act: -0.1700
Data Index: 1827563 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.3951. Min Act: -0.1700
Data Index: 3341001 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7239. Min Range: -3.7239
Max Act: 3.4265. Min Act: -0.1700
Data Index: 4794060 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19