Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.7421. Min Act: -0.1700
Data Index: 75297 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.7108. Min Act: -0.1700
Data Index: 6327332 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.6795. Min Act: -0.1700
Data Index: 3732176 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.6638. Min Act: -0.1700
Data Index: 1024715 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.6482. Min Act: -0.1700
Data Index: 565999 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.6013. Min Act: -0.1700
Data Index: 6735261 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5856. Min Act: -0.1700
Data Index: 7260827 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5699. Min Act: -0.1700
Data Index: 5415526 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5543. Min Act: -0.1700
Data Index: 8504161 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.6013. Min Act: -0.1700
Data Index: 5438814 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5856. Min Act: -0.1700
Data Index: 6673747 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5856. Min Act: -0.1700
Data Index: 5890418 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5856. Min Act: -0.1700
Data Index: 3513970 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5543. Min Act: -0.1700
Data Index: 5504586 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5543. Min Act: -0.1700
Data Index: 7035744 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5856. Min Act: -0.1700
Data Index: 7492857 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5699. Min Act: -0.1700
Data Index: 3828931 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5543. Min Act: -0.1700
Data Index: 1760632 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5230. Min Act: -0.1700
Data Index: 986882 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7421. Min Range: -3.7421
Max Act: 3.5386. Min Act: -0.1700
Data Index: 3799217 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19