Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.6104. Min Act: -0.1700
Data Index: 5335800 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3129418 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.4229. Min Act: -0.1700
Data Index: 472504 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.4229. Min Act: -0.1700
Data Index: 868205 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.3916. Min Act: -0.1700
Data Index: 3247387 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.3916. Min Act: -0.1700
Data Index: 2454741 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.3291. Min Act: -0.1700
Data Index: 1305676 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2979. Min Act: -0.1700
Data Index: 4410511 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2666. Min Act: -0.1700
Data Index: 6878902 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2979. Min Act: -0.1700
Data Index: 3574625 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 1362010 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2666. Min Act: -0.1700
Data Index: 2833161 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3076434 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 3349600 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 7022089 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 8131583 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 1713262 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 2736608 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2354. Min Act: -0.1700
Data Index: 267834 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6104. Min Range: -5.6104
Max Act: 5.2041. Min Act: -0.1700
Data Index: 509066 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19