Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 233 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.7338. Min Act: -0.1700
Data Index: 3182743 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6859. Min Act: -0.1700
Data Index: 7191210 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6538. Min Act: -0.1700
Data Index: 192556 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6377. Min Act: -0.1700
Data Index: 8080225 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6217. Min Act: -0.1700
Data Index: 1558626 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6217. Min Act: -0.1700
Data Index: 420416 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.6056. Min Act: -0.1700
Data Index: 938135 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.5734. Min Act: -0.1700
Data Index: 6072891 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.5895. Min Act: -0.1700
Data Index: 3124890 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.5573. Min Act: -0.1700
Data Index: 5899498 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.5411. Min Act: -0.1700
Data Index: 6598122 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.5411. Min Act: -0.1700
Data Index: 3658911 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4763. Min Act: -0.1700
Data Index: 718032 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4926. Min Act: -0.1700
Data Index: 3396818 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4926. Min Act: -0.1700
Data Index: 5905918 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4926. Min Act: -0.1700
Data Index: 7713099 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4763. Min Act: -0.1700
Data Index: 8048668 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4763. Min Act: -0.1700
Data Index: 6017994 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4763. Min Act: -0.1700
Data Index: 1118684 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7338. Min Range: -2.7338
Max Act: 2.4926. Min Act: -0.1700
Data Index: 6083461 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19