Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1818 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1414. Min Range: -6.1414
Max Act: 6.1414. Min Act: -0.1700
Data Index: 6130481 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.9852. Min Act: -0.1700
Data Index: 3340211 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.9227. Min Act: -0.1700
Data Index: 5815814 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4451674 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.9227. Min Act: -0.1700
Data Index: 6911 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8602. Min Act: -0.1700
Data Index: 3700391 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8914. Min Act: -0.1700
Data Index: 8637571 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8602. Min Act: -0.1700
Data Index: 3295687 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8289. Min Act: -0.1700
Data Index: 8518619 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7977. Min Act: -0.1700
Data Index: 6363103 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7977. Min Act: -0.1700
Data Index: 7628690 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8289. Min Act: -0.1700
Data Index: 28874 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7664. Min Act: -0.1700
Data Index: 6941398 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7977. Min Act: -0.1700
Data Index: 4214702 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7352. Min Act: -0.1700
Data Index: 1253638 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7352. Min Act: -0.1700
Data Index: 7792650 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5651544 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7039. Min Act: -0.1700
Data Index: 3244816 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5767269 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7039. Min Act: -0.1700
Data Index: 1336227 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19