Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3597. Min Range: -6.3597
Max Act: 6.3597. Min Act: -0.1700
Data Index: 1442985 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3597. Min Range: -6.3597
Max Act: 6.2972. Min Act: -0.1700
Data Index: 1686689 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3597. Min Range: -6.3597
Max Act: 6.2347. Min Act: -0.1700
Data Index: 3928185 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3597. Min Range: -6.3597
Max Act: 6.2347. Min Act: -0.1700
Data Index: 6954482 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.9222. Min Act: -0.1700
Data Index: 6765342 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.8910. Min Act: -0.1700
Data Index: 6806443 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.8285. Min Act: -0.1700
Data Index: 3596617 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.8285. Min Act: -0.1700
Data Index: 6757227 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7972. Min Act: -0.1700
Data Index: 3782135 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7972. Min Act: -0.1700
Data Index: 1632845 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1632846 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7347. Min Act: -0.1700
Data Index: 3773943 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7347. Min Act: -0.1700
Data Index: 1860404 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7035. Min Act: -0.1700
Data Index: 6227759 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7035. Min Act: -0.1700
Data Index: 283397 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7035. Min Act: -0.1700
Data Index: 4645735 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.7035. Min Act: -0.1700
Data Index: 4045993 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.6722. Min Act: -0.1700
Data Index: 3995059 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3866282 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3597. Min Range: -6.3597
Max Act: 5.6097. Min Act: -0.1700
Data Index: 8387452 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19