Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.3690. Min Act: -0.1700
Data Index: 2112648 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.3065. Min Act: -0.1700
Data Index: 3381914 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.2128. Min Act: -0.1700
Data Index: 7213823 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.2128. Min Act: -0.1700
Data Index: 7868442 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.1503. Min Act: -0.1700
Data Index: 6929444 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0878. Min Act: -0.1700
Data Index: 2581404 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0253. Min Act: -0.1700
Data Index: 4686356 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0253. Min Act: -0.1700
Data Index: 275968 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0253. Min Act: -0.1700
Data Index: 5441496 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0253. Min Act: -0.1700
Data Index: 1126790 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3690. Min Range: -6.3690
Max Act: 6.0253. Min Act: -0.1700
Data Index: 7793814 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9940. Min Act: -0.1700
Data Index: 344657 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9940. Min Act: -0.1700
Data Index: 5622577 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9628. Min Act: -0.1700
Data Index: 5930328 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9628. Min Act: -0.1700
Data Index: 6627968 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9003. Min Act: -0.1700
Data Index: 6263373 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9315. Min Act: -0.1700
Data Index: 3359794 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9003. Min Act: -0.1700
Data Index: 3603690 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9003. Min Act: -0.1700
Data Index: 3617352 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3690. Min Range: -6.3690
Max Act: 5.9003. Min Act: -0.1700
Data Index: 5567212 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19