Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.9878. Min Act: -0.1700
Data Index: 8590194 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0503. Min Range: -11.0503
Max Act: 11.0503. Min Act: -0.1700
Data Index: 7096333 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.9878. Min Act: -0.1700
Data Index: 3810655 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.9253. Min Act: -0.1700
Data Index: 1313565 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.8628. Min Act: -0.1700
Data Index: 7717134 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.8003. Min Act: -0.1700
Data Index: 3738735 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.7378. Min Act: -0.1700
Data Index: 8383320 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.7378. Min Act: -0.1700
Data Index: 2986117 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.6128. Min Act: -0.1700
Data Index: 7085792 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.6753. Min Act: -0.1700
Data Index: 8178893 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 2226647 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.6128. Min Act: -0.1700
Data Index: 635070 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.6128. Min Act: -0.1700
Data Index: 7528651 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 2977211 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 4340163 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 6495638 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 8400407 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 1911793 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1699
Data Index: 5560793 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0503. Min Range: -11.0503
Max Act: 10.5503. Min Act: -0.1700
Data Index: 3529339 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19