Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.7102. Min Act: -0.1700
Data Index: 5601284 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.5852. Min Act: -0.1700
Data Index: 2198357 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.5539. Min Act: -0.1700
Data Index: 2223354 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.4914. Min Act: -0.1700
Data Index: 1994419 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3977. Min Act: -0.1700
Data Index: 2410775 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3977. Min Act: -0.1700
Data Index: 3857216 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3664. Min Act: -0.1700
Data Index: 1164194 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3664. Min Act: -0.1700
Data Index: 743323 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3664. Min Act: -0.1700
Data Index: 7536147 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3664. Min Act: -0.1700
Data Index: 5221509 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3352. Min Act: -0.1700
Data Index: 5155810 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3039. Min Act: -0.1700
Data Index: 1164195 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3352. Min Act: -0.1700
Data Index: 7572488 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.3039. Min Act: -0.1700
Data Index: 7905838 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.2727. Min Act: -0.1700
Data Index: 4721134 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.2414. Min Act: -0.1700
Data Index: 4970665 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.2414. Min Act: -0.1700
Data Index: 6875746 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.2414. Min Act: -0.1700
Data Index: 606585 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.1789. Min Act: -0.1700
Data Index: 1281426 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7102. Min Range: -6.7102
Max Act: 6.1789. Min Act: -0.1700
Data Index: 7556728 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19