Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.7351. Min Act: -0.1700
Data Index: 1808110 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.7039. Min Act: -0.1700
Data Index: 7143105 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3702274 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.6101. Min Act: -0.1700
Data Index: 805323 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.5789. Min Act: -0.1700
Data Index: 7815515 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.5476. Min Act: -0.1700
Data Index: 966930 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.5164. Min Act: -0.1700
Data Index: 6539322 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4851. Min Act: -0.1700
Data Index: 78348 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 4604859 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 7896112 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 1901967 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4539. Min Act: -0.1700
Data Index: 8708819 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.3914. Min Act: -0.1700
Data Index: 2859873 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 8437197 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 228645 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.4226. Min Act: -0.1700
Data Index: 805326 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.3914. Min Act: -0.1700
Data Index: 254378 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.3914. Min Act: -0.1700
Data Index: 3982172 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.3601. Min Act: -0.1700
Data Index: 1430101 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7351. Min Range: -5.7351
Max Act: 5.3601. Min Act: -0.1700
Data Index: 311411 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19