Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.5610. Min Act: -0.1700
Data Index: 1014009 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.6235. Min Act: -0.1700
Data Index: 2361826 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.5610. Min Act: -0.1700
Data Index: 4911127 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.5297. Min Act: -0.1700
Data Index: 2300468 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4985. Min Act: -0.1700
Data Index: 7237574 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4985. Min Act: -0.1700
Data Index: 1364919 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4672. Min Act: -0.1700
Data Index: 8740459 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4985. Min Act: -0.1700
Data Index: 8788617 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4360. Min Act: -0.1700
Data Index: 6548405 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4360. Min Act: -0.1700
Data Index: 4320501 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 8520467 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4360. Min Act: -0.1700
Data Index: 8824193 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6222942 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 7222880 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 351932 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6479338 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3382519 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6099540 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4360. Min Act: -0.1700
Data Index: 7395608 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6235. Min Range: -5.6235
Max Act: 5.4047. Min Act: -0.1700
Data Index: 5566970 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19