Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3494 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.1585. Min Act: -0.1700
Data Index: 3066473 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.1585. Min Act: -0.1700
Data Index: 6785157 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.1585. Min Act: -0.1700
Data Index: 4582077 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.0022. Min Act: -0.1700
Data Index: 3341636 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.0335. Min Act: -0.1700
Data Index: 3772366 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.0022. Min Act: -0.1700
Data Index: 5712603 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1585. Min Range: -8.1585
Max Act: 8.0022. Min Act: -0.1700
Data Index: 8502625 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 2530167 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 8025166 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9397. Min Act: -0.1700
Data Index: 6597314 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 2760997 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9710. Min Act: -0.1700
Data Index: 1838473 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 987327 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 5274967 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9397. Min Act: -0.1700
Data Index: 6400801 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.8772. Min Act: -0.1700
Data Index: 2415639 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 7475189 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 8475707 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.9085. Min Act: -0.1700
Data Index: 4329643 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1585. Min Range: -8.1585
Max Act: 7.8772. Min Act: -0.1700
Data Index: 5717439 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19