Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4729. Min Range: -7.4729
Max Act: 7.4729. Min Act: -0.1700
Data Index: 7762332 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.8792. Min Act: -0.1700
Data Index: 7488059 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.8479. Min Act: -0.1700
Data Index: 8757989 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.7854. Min Act: -0.1700
Data Index: 5653948 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.7854. Min Act: -0.1700
Data Index: 5375460 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.6917. Min Act: -0.1700
Data Index: 6982947 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.6917. Min Act: -0.1700
Data Index: 3335582 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5979. Min Act: -0.1700
Data Index: 2942206 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5979. Min Act: -0.1700
Data Index: 1631951 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5667. Min Act: -0.1700
Data Index: 8155377 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5667. Min Act: -0.1700
Data Index: 578968 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5354. Min Act: -0.1700
Data Index: 2422848 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.5354. Min Act: -0.1700
Data Index: 3787753 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.4729. Min Act: -0.1700
Data Index: 8096967 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.4417. Min Act: -0.1700
Data Index: 1747182 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.4417. Min Act: -0.1700
Data Index: 3317666 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.4417. Min Act: -0.1700
Data Index: 5678357 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.4104. Min Act: -0.1700
Data Index: 2115099 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.3792. Min Act: -0.1700
Data Index: 8182628 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4729. Min Range: -7.4729
Max Act: 6.3479. Min Act: -0.1700
Data Index: 1680407 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19