Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.3542. Min Act: -0.1700
Data Index: 4028735 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.1979. Min Act: -0.1700
Data Index: 5255625 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.1979. Min Act: -0.1700
Data Index: 431181 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.1042. Min Act: -0.1700
Data Index: 8459334 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0729. Min Act: -0.1700
Data Index: 925644 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0417. Min Act: -0.1700
Data Index: 3884090 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0417. Min Act: -0.1700
Data Index: 692570 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0104. Min Act: -0.1700
Data Index: 5269761 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0104. Min Act: -0.1700
Data Index: 5883491 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3542. Min Range: -6.3542
Max Act: 6.0104. Min Act: -0.1700
Data Index: 5497156 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9792. Min Act: -0.1700
Data Index: 347146 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6441598 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9479. Min Act: -0.1700
Data Index: 1234389 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9479. Min Act: -0.1700
Data Index: 3719069 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9167. Min Act: -0.1700
Data Index: 5298391 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9167. Min Act: -0.1700
Data Index: 4838540 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.8854. Min Act: -0.1700
Data Index: 2284893 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.9167. Min Act: -0.1700
Data Index: 3274189 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.8854. Min Act: -0.1700
Data Index: 823204 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3542. Min Range: -6.3542
Max Act: 5.8854. Min Act: -0.1700
Data Index: 6038172 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19