Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2042. Min Range: -6.2042
Max Act: 6.2042. Min Act: -0.1700
Data Index: 7703633 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2042. Min Range: -6.2042
Max Act: 6.0480. Min Act: -0.1700
Data Index: 7543884 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2042. Min Range: -6.2042
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5584918 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4188727 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.9230. Min Act: -0.1700
Data Index: 1104309 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.8917. Min Act: -0.1700
Data Index: 3836767 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5486129 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.8605. Min Act: -0.1700
Data Index: 6366589 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1799528 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7980. Min Act: -0.1700
Data Index: 8622824 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.8605. Min Act: -0.1700
Data Index: 4457160 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7980. Min Act: -0.1700
Data Index: 13003 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7980. Min Act: -0.1700
Data Index: 6619588 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 2762358 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 4727413 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 5219803 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 828591 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 5976970 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7667. Min Act: -0.1700
Data Index: 6776639 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2042. Min Range: -6.2042
Max Act: 5.7355. Min Act: -0.1700
Data Index: 960564 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19