Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3627 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.4278. Min Act: -0.1700
Data Index: 1923438 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.3653. Min Act: -0.1700
Data Index: 1319516 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.3653. Min Act: -0.1700
Data Index: 3116018 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.3965. Min Act: -0.1699
Data Index: 6241985 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.3340. Min Act: -0.1700
Data Index: 6122221 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2715. Min Act: -0.1700
Data Index: 8174427 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2715. Min Act: -0.1700
Data Index: 7798758 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2715. Min Act: -0.1700
Data Index: 6522430 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2715. Min Act: -0.1700
Data Index: 8452269 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2715. Min Act: -0.1700
Data Index: 406203 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 1792211 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 1746166 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 7592610 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 4048676 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 7247145 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2402. Min Act: -0.1700
Data Index: 7736196 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2090. Min Act: -0.1700
Data Index: 5544769 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.1777. Min Act: -0.1700
Data Index: 4541926 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2090. Min Act: -0.1700
Data Index: 4559719 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.2090. Min Act: -0.1700
Data Index: 2326525 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19