Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 994 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5199. Min Range: -4.5199
Max Act: 4.5199. Min Act: -0.1700
Data Index: 1772404 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5199. Min Range: -4.5199
Max Act: 4.2699. Min Act: -0.1700
Data Index: 2047282 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5199. Min Range: -4.5199
Max Act: 4.0198. Min Act: -0.1700
Data Index: 8735771 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5199. Min Range: -4.5199
Max Act: 4.0198. Min Act: -0.1700
Data Index: 7044690 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5199. Min Range: -4.5199
Max Act: 4.0198. Min Act: -0.1700
Data Index: 5629848 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.9573. Min Act: -0.1700
Data Index: 7279092 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.9573. Min Act: -0.1700
Data Index: 7707537 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.9260. Min Act: -0.1700
Data Index: 284486 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8948. Min Act: -0.1700
Data Index: 8153131 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8322. Min Act: -0.1700
Data Index: 7397779 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8635. Min Act: -0.1700
Data Index: 5289661 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8322. Min Act: -0.1700
Data Index: 6091537 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8322. Min Act: -0.1700
Data Index: 4938346 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8322. Min Act: -0.1700
Data Index: 8371493 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.7697. Min Act: -0.1700
Data Index: 5710205 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8010. Min Act: -0.1700
Data Index: 6247198 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.8010. Min Act: -0.1700
Data Index: 1753301 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.7697. Min Act: -0.1700
Data Index: 3516899 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.7697. Min Act: -0.1700
Data Index: 3068004 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5199. Min Range: -4.5199
Max Act: 3.7697. Min Act: -0.1700
Data Index: 7308211 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19