Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3272. Min Range: -7.3272
Max Act: 7.3272. Min Act: -0.1700
Data Index: 5888551 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3272. Min Range: -7.3272
Max Act: 7.2647. Min Act: -0.1700
Data Index: 7543027 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.8272. Min Act: -0.1700
Data Index: 969228 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.7647. Min Act: -0.1700
Data Index: 3342850 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.7334. Min Act: -0.1700
Data Index: 5267386 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.4209. Min Act: -0.1700
Data Index: 511420 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.3897. Min Act: -0.1700
Data Index: 7232572 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.3272. Min Act: -0.1700
Data Index: 531474 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2959. Min Act: -0.1700
Data Index: 1852430 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3289983 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2647. Min Act: -0.1700
Data Index: 822327 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2959. Min Act: -0.1700
Data Index: 3087982 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2647. Min Act: -0.1700
Data Index: 6169269 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2647. Min Act: -0.1700
Data Index: 8015764 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2334. Min Act: -0.1700
Data Index: 8012593 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2022. Min Act: -0.1700
Data Index: 1760963 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.2022. Min Act: -0.1700
Data Index: 5547137 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.1709. Min Act: -0.1700
Data Index: 581636 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.1709. Min Act: -0.1700
Data Index: 962515 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3272. Min Range: -7.3272
Max Act: 6.1709. Min Act: -0.1700
Data Index: 1054569 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19