Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1992 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.8324. Min Act: -0.1700
Data Index: 4997468 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.8005. Min Act: -0.1700
Data Index: 4837836 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7687. Min Act: -0.1700
Data Index: 1945419 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.8005. Min Act: -0.1700
Data Index: 2121712 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7846. Min Act: -0.1700
Data Index: 6108371 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7687. Min Act: -0.1700
Data Index: 7654824 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7527. Min Act: -0.1700
Data Index: 6989078 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7527. Min Act: -0.1700
Data Index: 4129122 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7687. Min Act: -0.1700
Data Index: 549671 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7527. Min Act: -0.1700
Data Index: 6152392 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7367. Min Act: -0.1700
Data Index: 2555109 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7208. Min Act: -0.1700
Data Index: 5084737 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7367. Min Act: -0.1700
Data Index: 8747329 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7208. Min Act: -0.1700
Data Index: 5204530 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7367. Min Act: -0.1700
Data Index: 3723308 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7208. Min Act: -0.1700
Data Index: 2298074 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7527. Min Act: -0.1700
Data Index: 2892760 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7367. Min Act: -0.1700
Data Index: 7652303 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7048. Min Act: -0.1700
Data Index: 6824589 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8324. Min Range: -2.8324
Max Act: 2.7367. Min Act: -0.1700
Data Index: 6981574 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19