Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1896 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4503. Min Range: -5.4503
Max Act: 5.4503. Min Act: -0.1700
Data Index: 8367833 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.8878. Min Act: -0.1700
Data Index: 3110561 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.8566. Min Act: -0.1700
Data Index: 8019213 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.8566. Min Act: -0.1700
Data Index: 531604 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.8566. Min Act: -0.1700
Data Index: 7870780 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 4751271 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.8253. Min Act: -0.1700
Data Index: 612684 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 3772505 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 3319551 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 7866480 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 8434188 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7628. Min Act: -0.1700
Data Index: 8784663 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7941. Min Act: -0.1700
Data Index: 5322470 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7628. Min Act: -0.1700
Data Index: 2072792 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7628. Min Act: -0.1700
Data Index: 8064316 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7628. Min Act: -0.1700
Data Index: 1664574 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7316. Min Act: -0.1700
Data Index: 694996 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7316. Min Act: -0.1700
Data Index: 227597 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7316. Min Act: -0.1700
Data Index: 4341520 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4503. Min Range: -5.4503
Max Act: 4.7003. Min Act: -0.1700
Data Index: 3656658 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19