Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.6021. Min Act: -0.1700
Data Index: 6563791 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.5396. Min Act: -0.1700
Data Index: 4265425 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.5709. Min Act: -0.1700
Data Index: 4583698 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.4146. Min Act: -0.1700
Data Index: 4291990 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.3209. Min Act: -0.1700
Data Index: 921817 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.3209. Min Act: -0.1700
Data Index: 4763146 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.3209. Min Act: -0.1700
Data Index: 318496 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.2271. Min Act: -0.1700
Data Index: 1854183 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.2584. Min Act: -0.1700
Data Index: 2421070 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.1646. Min Act: -0.1700
Data Index: 2546468 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.1646. Min Act: -0.1700
Data Index: 3149200 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.1334. Min Act: -0.1700
Data Index: 3600314 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.0396. Min Act: -0.1700
Data Index: 7456662 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.0709. Min Act: -0.1700
Data Index: 8208407 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.1021. Min Act: -0.1700
Data Index: 6474077 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.1021. Min Act: -0.1700
Data Index: 7801893 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6021. Min Range: -7.6021
Max Act: 6.9771. Min Act: -0.1700
Data Index: 1944312 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.0396. Min Act: -0.1700
Data Index: 6362746 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.0084. Min Act: -0.1700
Data Index: 5855593 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6021. Min Range: -7.6021
Max Act: 7.0396. Min Act: -0.1700
Data Index: 1384639 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19