Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.5152. Min Act: -0.1700
Data Index: 153073 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.5314. Min Act: -0.1700
Data Index: 311444 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4990. Min Act: -0.1700
Data Index: 8141472 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.5152. Min Act: -0.1700
Data Index: 5481329 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4828. Min Act: -0.1700
Data Index: 5317486 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4990. Min Act: -0.1700
Data Index: 2318854 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4503. Min Act: -0.1700
Data Index: 3246098 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 8350226 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4665. Min Act: -0.1700
Data Index: 6649052 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 2998049 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4177. Min Act: -0.1700
Data Index: 8736413 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4177. Min Act: -0.1700
Data Index: 5450516 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 4352912 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 1097205 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4177. Min Act: -0.1700
Data Index: 6176311 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 7002622 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4177. Min Act: -0.1700
Data Index: 7462 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4340. Min Act: -0.1700
Data Index: 3854588 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4014. Min Act: -0.1700
Data Index: 924350 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5314. Min Range: -2.5314
Max Act: 2.4177. Min Act: -0.1700
Data Index: 7503660 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19