Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5170 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.7282. Min Act: -0.1700
Data Index: 1196771 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.6962. Min Act: -0.1700
Data Index: 4419951 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.6481. Min Act: -0.1700
Data Index: 5512581 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.6320. Min Act: -0.1700
Data Index: 5325045 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.6160. Min Act: -0.1700
Data Index: 1846907 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5999. Min Act: -0.1700
Data Index: 7994281 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.6160. Min Act: -0.1700
Data Index: 5636682 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5838. Min Act: -0.1700
Data Index: 8274937 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5838. Min Act: -0.1700
Data Index: 2694949 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 5635259 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5838. Min Act: -0.1700
Data Index: 5840674 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 6326928 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 3298090 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 456002 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 5863551 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 1138709 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 5721377 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 2081672 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 983903 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7282. Min Range: -2.7282
Max Act: 2.5677. Min Act: -0.1700
Data Index: 5624757 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19