Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 453 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.7003. Min Act: -0.1700
Data Index: 7799808 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.6066. Min Act: -0.1700
Data Index: 5770698 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5441. Min Act: -0.1700
Data Index: 2118300 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5128. Min Act: -0.1700
Data Index: 954342 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4816. Min Act: -0.1700
Data Index: 8694306 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.5128. Min Act: -0.1700
Data Index: 1630048 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4816. Min Act: -0.1700
Data Index: 4453290 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4191. Min Act: -0.1700
Data Index: 8323797 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 3115626 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4503. Min Act: -0.1700
Data Index: 3409808 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4191. Min Act: -0.1700
Data Index: 7154094 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.4191. Min Act: -0.1700
Data Index: 7536460 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3878. Min Act: -0.1700
Data Index: 2866029 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3566. Min Act: -0.1700
Data Index: 3578466 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3566. Min Act: -0.1700
Data Index: 7848171 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.2941. Min Act: -0.1700
Data Index: 5362937 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 7468952 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 2866028 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 954346 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7003. Min Range: -5.7003
Max Act: 5.3253. Min Act: -0.1700
Data Index: 7801401 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19