Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1283 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.8209. Min Act: -0.1700
Data Index: 3032869 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.7271. Min Act: -0.1700
Data Index: 7003838 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.6021. Min Act: -0.1700
Data Index: 7772857 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.5084. Min Act: -0.1700
Data Index: 7520768 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.4771. Min Act: -0.1700
Data Index: 1568264 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.3521. Min Act: -0.1700
Data Index: 6523663 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.3521. Min Act: -0.1700
Data Index: 7431940 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.2896. Min Act: -0.1700
Data Index: 1568262 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.2584. Min Act: -0.1700
Data Index: 403223 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2855425 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8209. Min Range: -6.8209
Max Act: 6.0084. Min Act: -0.1700
Data Index: 2578937 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.9459. Min Act: -0.1700
Data Index: 4602349 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.9146. Min Act: -0.1700
Data Index: 3848244 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8521. Min Act: -0.1700
Data Index: 851054 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8834. Min Act: -0.1700
Data Index: 694840 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8521. Min Act: -0.1700
Data Index: 8737993 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8521. Min Act: -0.1700
Data Index: 5977459 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8209. Min Act: -0.1700
Data Index: 727936 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8209. Min Act: -0.1700
Data Index: 4607409 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8209. Min Range: -6.8209
Max Act: 5.8209. Min Act: -0.1700
Data Index: 6736879 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19