Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4785 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2227. Min Range: -4.2227
Max Act: 4.2227. Min Act: -0.1700
Data Index: 1165444 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2227. Min Range: -4.2227
Max Act: 4.1915. Min Act: -0.1700
Data Index: 4566528 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2227. Min Range: -4.2227
Max Act: 4.2227. Min Act: -0.1700
Data Index: 8089678 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2227. Min Range: -4.2227
Max Act: 4.1915. Min Act: -0.1700
Data Index: 8741432 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2227. Min Range: -4.2227
Max Act: 4.0665. Min Act: -0.1700
Data Index: 1996500 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.9727. Min Act: -0.1700
Data Index: 682321 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.9414. Min Act: -0.1700
Data Index: 7423302 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.9102. Min Act: -0.1700
Data Index: 950573 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.9102. Min Act: -0.1700
Data Index: 6501594 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8789. Min Act: -0.1700
Data Index: 4608918 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.9102. Min Act: -0.1700
Data Index: 5567280 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8789. Min Act: -0.1700
Data Index: 5365239 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8789. Min Act: -0.1700
Data Index: 2633265 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8476. Min Act: -0.1700
Data Index: 2802707 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8320. Min Act: -0.1700
Data Index: 1829968 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8476. Min Act: -0.1700
Data Index: 6806560 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8320. Min Act: -0.1700
Data Index: 6200691 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8164. Min Act: -0.1700
Data Index: 6369883 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8476. Min Act: -0.1700
Data Index: 3695673 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2227. Min Range: -4.2227
Max Act: 3.8320. Min Act: -0.1700
Data Index: 5260147 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19