Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.3647. Min Act: -0.1700
Data Index: 2871765 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.0834. Min Act: -0.1700
Data Index: 4662068 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.0522. Min Act: -0.1700
Data Index: 1138375 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.0522. Min Act: -0.1700
Data Index: 8310975 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.0522. Min Act: -0.1700
Data Index: 2145853 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3647. Min Range: -7.3647
Max Act: 7.0209. Min Act: -0.1700
Data Index: 1950916 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.9897. Min Act: -0.1700
Data Index: 892390 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.9897. Min Act: -0.1700
Data Index: 7182054 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.9272. Min Act: -0.1700
Data Index: 6005300 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.9584. Min Act: -0.1700
Data Index: 1094583 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.9272. Min Act: -0.1700
Data Index: 3569816 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8959. Min Act: -0.1700
Data Index: 6505289 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8959. Min Act: -0.1700
Data Index: 5232274 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8959. Min Act: -0.1700
Data Index: 4965807 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8647. Min Act: -0.1700
Data Index: 2095540 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6714826 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6420893 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8647. Min Act: -0.1700
Data Index: 7343259 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8959. Min Act: -0.1700
Data Index: 3919135 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3647. Min Range: -7.3647
Max Act: 6.8334. Min Act: -0.1700
Data Index: 6774734 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19