Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.2943. Min Act: -0.1700
Data Index: 3170916 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.2943. Min Act: -0.1700
Data Index: 7497429 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.1693. Min Act: -0.1700
Data Index: 711224 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.0755. Min Act: -0.1700
Data Index: 4644418 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.1067. Min Act: -0.1700
Data Index: 711223 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.0442. Min Act: -0.1700
Data Index: 2991641 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2943. Min Range: -4.2943
Max Act: 4.0130. Min Act: -0.1700
Data Index: 1989119 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9817. Min Act: -0.1700
Data Index: 2376597 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9817. Min Act: -0.1700
Data Index: 8290835 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9817. Min Act: -0.1700
Data Index: 8058136 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9817. Min Act: -0.1700
Data Index: 7939536 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9817. Min Act: -0.1700
Data Index: 3330137 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9348. Min Act: -0.1700
Data Index: 3621914 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9192. Min Act: -0.1700
Data Index: 8102189 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9348. Min Act: -0.1700
Data Index: 1904024 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9348. Min Act: -0.1700
Data Index: 478440 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9192. Min Act: -0.1700
Data Index: 3989855 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9192. Min Act: -0.1700
Data Index: 4762904 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9035. Min Act: -0.1700
Data Index: 6856947 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2943. Min Range: -4.2943
Max Act: 3.9192. Min Act: -0.1700
Data Index: 860672 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19