Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6385. Min Range: -6.6385
Max Act: 6.6385. Min Act: -0.1700
Data Index: 6676214 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6385. Min Range: -6.6385
Max Act: 6.3572. Min Act: -0.1700
Data Index: 8663133 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6385. Min Range: -6.6385
Max Act: 6.1697. Min Act: -0.1700
Data Index: 5383691 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6385. Min Range: -6.6385
Max Act: 6.0760. Min Act: -0.1700
Data Index: 7988202 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.9197. Min Act: -0.1700
Data Index: 4651262 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.8572. Min Act: -0.1700
Data Index: 2226497 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.8260. Min Act: -0.1700
Data Index: 1353594 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.8260. Min Act: -0.1700
Data Index: 8634452 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.8260. Min Act: -0.1700
Data Index: 5114729 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1338142 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7947. Min Act: -0.1700
Data Index: 1338140 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7635. Min Act: -0.1700
Data Index: 2235824 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7635. Min Act: -0.1700
Data Index: 7646419 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7322. Min Act: -0.1700
Data Index: 3371123 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.7010. Min Act: -0.1700
Data Index: 3666709 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.6697. Min Act: -0.1700
Data Index: 32417 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.6697. Min Act: -0.1700
Data Index: 2774680 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.6697. Min Act: -0.1700
Data Index: 1672582 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.6697. Min Act: -0.1700
Data Index: 7813253 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6385. Min Range: -6.6385
Max Act: 5.6697. Min Act: -0.1700
Data Index: 1338138 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19