Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.7209. Min Act: -0.1700
Data Index: 3433313 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.7036. Min Act: -0.1700
Data Index: 215590 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6689. Min Act: -0.1700
Data Index: 3308522 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6428. Min Act: -0.1700
Data Index: 1416905 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6428. Min Act: -0.1700
Data Index: 1510732 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6515. Min Act: -0.1700
Data Index: 3798540 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6340. Min Act: -0.1700
Data Index: 8720578 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6340. Min Act: -0.1700
Data Index: 7084609 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6340. Min Act: -0.1700
Data Index: 1226355 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6253. Min Act: -0.1700
Data Index: 7516480 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6166. Min Act: -0.1700
Data Index: 2367526 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6253. Min Act: -0.1700
Data Index: 905347 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6253. Min Act: -0.1700
Data Index: 6887941 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6253. Min Act: -0.1700
Data Index: 3533974 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6079. Min Act: -0.1700
Data Index: 7240970 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6166. Min Act: -0.1700
Data Index: 2999954 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6079. Min Act: -0.1700
Data Index: 3431470 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6166. Min Act: -0.1700
Data Index: 2556846 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6166. Min Act: -0.1700
Data Index: 6876114 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7209. Min Range: -1.7209
Max Act: 1.6166. Min Act: -0.1700
Data Index: 4028221 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19