Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.4152. Min Act: -0.1700
Data Index: 6612807 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.3215. Min Act: -0.1700
Data Index: 5906420 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.3215. Min Act: -0.1700
Data Index: 7376899 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.2590. Min Act: -0.1700
Data Index: 8311106 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.2902. Min Act: -0.1700
Data Index: 6557342 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.2277. Min Act: -0.1700
Data Index: 2174934 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.2277. Min Act: -0.1700
Data Index: 7815673 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.1027. Min Act: -0.1700
Data Index: 1723336 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.1027. Min Act: -0.1700
Data Index: 2202586 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.1027. Min Act: -0.1700
Data Index: 8402486 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.0090. Min Act: -0.1700
Data Index: 8726219 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4152. Min Range: -6.4152
Max Act: 6.0090. Min Act: -0.1700
Data Index: 3256297 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9777. Min Act: -0.1700
Data Index: 4563446 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 1507559 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 4749000 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 1065076 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 945809 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.8527. Min Act: -0.1700
Data Index: 1137578 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.9152. Min Act: -0.1700
Data Index: 1647800 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4152. Min Range: -6.4152
Max Act: 5.8527. Min Act: -0.1700
Data Index: 573261 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19