Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 149 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 8383954 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 8272698 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 3099559 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7064690 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7340738 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 2199591 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7413287 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6806. Min Act: -0.1700
Data Index: 7789081 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.6493. Min Act: -0.1700
Data Index: 6366793 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.5868. Min Act: -0.1700
Data Index: 2199594 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.5556. Min Act: -0.1700
Data Index: 7792176 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.5556. Min Act: -0.1700
Data Index: 2199593 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4931. Min Act: -0.1700
Data Index: 7822401 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4931. Min Act: -0.1700
Data Index: 6957478 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 4894770 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 2515560 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4931. Min Act: -0.1700
Data Index: 8729151 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 536917 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 2199596 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7743. Min Range: -6.7743
Max Act: 6.4618. Min Act: -0.1700
Data Index: 2886061 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19