Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.5913. Min Act: -0.1700
Data Index: 3422617 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.3413. Min Act: -0.1700
Data Index: 8360882 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.4038. Min Act: -0.1700
Data Index: 1130834 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.2788. Min Act: -0.1700
Data Index: 8113971 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.2788. Min Act: -0.1700
Data Index: 7847979 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.1538. Min Act: -0.1700
Data Index: 676073 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.5913. Min Range: -15.5913
Max Act: 15.0288. Min Act: -0.1697
Data Index: 7800580 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.9663. Min Act: -0.1700
Data Index: 8514931 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.9038. Min Act: -0.1700
Data Index: 1424103 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.9038. Min Act: -0.1700
Data Index: 6972389 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.8413. Min Act: -0.1700
Data Index: 6739590 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.8413. Min Act: -0.1700
Data Index: 1837171 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.5913. Min Act: -0.1700
Data Index: 3312073 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.5913. Min Act: -0.1700
Data Index: 8824488 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.5288. Min Act: -0.1699
Data Index: 8329580 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.5288. Min Act: -0.1700
Data Index: 4605322 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.5288. Min Act: -0.1700
Data Index: 7089677 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.4663. Min Act: -0.1700
Data Index: 2603266 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.4663. Min Act: -0.1700
Data Index: 1130841 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.5913. Min Range: -15.5913
Max Act: 14.4038. Min Act: -0.1700
Data Index: 5280741 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19