Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.6742. Min Act: -0.1700
Data Index: 6949129 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.5805. Min Act: -0.1700
Data Index: 2282212 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4867. Min Act: -0.1700
Data Index: 2931189 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4867. Min Act: -0.1700
Data Index: 5208080 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4867. Min Act: -0.1700
Data Index: 2749399 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4867. Min Act: -0.1700
Data Index: 2282211 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4555. Min Act: -0.1700
Data Index: 5406127 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4555. Min Act: -0.1700
Data Index: 7172644 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4555. Min Act: -0.1700
Data Index: 3815627 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4555. Min Act: -0.1700
Data Index: 2557096 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4555. Min Act: -0.1700
Data Index: 3112280 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4242. Min Act: -0.1700
Data Index: 6586523 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4242. Min Act: -0.1700
Data Index: 6789273 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4242. Min Act: -0.1700
Data Index: 4842565 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.4242. Min Act: -0.1700
Data Index: 585348 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.3617. Min Act: -0.1700
Data Index: 6353305 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.3930. Min Act: -0.1700
Data Index: 5517095 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.3617. Min Act: -0.1700
Data Index: 665633 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.3930. Min Act: -0.1700
Data Index: 7318484 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6742. Min Range: -4.6742
Max Act: 4.3930. Min Act: -0.1700
Data Index: 4657505 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19