Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.5349. Min Act: -0.1700
Data Index: 5429125 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.2407. Min Act: -0.1700
Data Index: 1213582 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.2076. Min Act: -0.1700
Data Index: 7110662 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.2076. Min Act: -0.1700
Data Index: 6875775 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1910. Min Act: -0.1700
Data Index: 5626422 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1744. Min Act: -0.1700
Data Index: 721226 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1744. Min Act: -0.1700
Data Index: 2317840 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1744. Min Act: -0.1700
Data Index: 6380949 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1744. Min Act: -0.1700
Data Index: 4643333 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 1305792 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1744. Min Act: -0.1700
Data Index: 6826871 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 2561497 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 2585214 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 3439068 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1411. Min Act: -0.1700
Data Index: 3172736 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 1120658 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1578. Min Act: -0.1700
Data Index: 2556331 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1244. Min Act: -0.1700
Data Index: 2289926 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1411. Min Act: -0.1700
Data Index: 4253691 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5349. Min Range: -2.5349
Max Act: 2.1244. Min Act: -0.1700
Data Index: 2709228 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19