Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.5337. Min Act: -0.1700
Data Index: 2243542 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.5024. Min Act: -0.1700
Data Index: 7632060 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.5024. Min Act: -0.1700
Data Index: 6672614 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.3457. Min Act: -0.1700
Data Index: 7818708 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.3613. Min Act: -0.1700
Data Index: 4021054 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2986. Min Act: -0.1700
Data Index: 7368675 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2986. Min Act: -0.1700
Data Index: 5012489 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2357. Min Act: -0.1700
Data Index: 1732758 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2200. Min Act: -0.1700
Data Index: 4882293 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 75578 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2515. Min Act: -0.1700
Data Index: 397730 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2200. Min Act: -0.1700
Data Index: 8655154 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 5287923 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 8201351 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 4005522 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 4604347 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 7256949 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.2043. Min Act: -0.1700
Data Index: 8393124 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.1886. Min Act: -0.1700
Data Index: 6973466 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5337. Min Range: -3.5337
Max Act: 3.1886. Min Act: -0.1700
Data Index: 6142881 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19