Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1024. Min Range: -10.1024
Max Act: 10.0399. Min Act: -0.1700
Data Index: 4850011 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1024. Min Range: -10.1024
Max Act: 10.1024. Min Act: -0.1700
Data Index: 2033580 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.9774. Min Act: -0.1700
Data Index: 7774226 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.9774. Min Act: -0.1700
Data Index: 5579252 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.9149. Min Act: -0.1700
Data Index: 3263274 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.7274. Min Act: -0.1700
Data Index: 2170070 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6649. Min Act: -0.1700
Data Index: 8739942 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6649. Min Act: -0.1700
Data Index: 188412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6649. Min Act: -0.1700
Data Index: 1384080 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6649. Min Act: -0.1700
Data Index: 7486289 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6024. Min Act: -0.1700
Data Index: 4457449 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6024. Min Act: -0.1700
Data Index: 7735395 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6024. Min Act: -0.1700
Data Index: 5772527 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.5399. Min Act: -0.1700
Data Index: 3041740 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.5399. Min Act: -0.1700
Data Index: 8660151 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6024. Min Act: -0.1700
Data Index: 7027451 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.6024. Min Act: -0.1700
Data Index: 2086030 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.4774. Min Act: -0.1700
Data Index: 7276128 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.4774. Min Act: -0.1700
Data Index: 1600631 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1024. Min Range: -10.1024
Max Act: 9.5399. Min Act: -0.1700
Data Index: 7389700 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19