Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.5148. Min Act: -0.1700
Data Index: 514834 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.4365. Min Act: -0.1700
Data Index: 514833 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.4365. Min Act: -0.1700
Data Index: 8182824 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.3267. Min Act: -0.1700
Data Index: 2979277 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.3424. Min Act: -0.1700
Data Index: 2534097 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2953. Min Act: -0.1700
Data Index: 874866 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2796. Min Act: -0.1700
Data Index: 8687282 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2796. Min Act: -0.1700
Data Index: 7546728 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2639. Min Act: -0.1700
Data Index: 7820086 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2639. Min Act: -0.1700
Data Index: 5665111 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2639. Min Act: -0.1700
Data Index: 4190759 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2482. Min Act: -0.1700
Data Index: 1933971 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2325. Min Act: -0.1700
Data Index: 5612816 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2325. Min Act: -0.1700
Data Index: 3245237 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2482. Min Act: -0.1700
Data Index: 2490051 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2482. Min Act: -0.1700
Data Index: 6393949 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2168. Min Act: -0.1700
Data Index: 6322888 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2010. Min Act: -0.1700
Data Index: 7742164 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.2010. Min Act: -0.1700
Data Index: 7404469 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5148. Min Range: -3.5148
Max Act: 3.1853. Min Act: -0.1700
Data Index: 4099787 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19