Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.6185. Min Act: -0.1700
Data Index: 3883662 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.5873. Min Act: -0.1700
Data Index: 6597352 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.5873. Min Act: -0.1700
Data Index: 6908458 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.5248. Min Act: -0.1700
Data Index: 6513139 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4935. Min Act: -0.1700
Data Index: 8008519 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4310. Min Act: -0.1700
Data Index: 2881261 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4623. Min Act: -0.1700
Data Index: 2179422 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4935. Min Act: -0.1700
Data Index: 6557876 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4623. Min Act: -0.1700
Data Index: 1034773 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4623. Min Act: -0.1700
Data Index: 6609260 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4310. Min Act: -0.1700
Data Index: 1588232 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4623. Min Act: -0.1700
Data Index: 2250846 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3998. Min Act: -0.1700
Data Index: 4352061 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3998. Min Act: -0.1700
Data Index: 3687942 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.4310. Min Act: -0.1700
Data Index: 6000632 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3685. Min Act: -0.1700
Data Index: 5396435 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3685. Min Act: -0.1700
Data Index: 2084845 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3373. Min Act: -0.1700
Data Index: 8617403 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3685. Min Act: -0.1700
Data Index: 947606 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6185. Min Range: -4.6185
Max Act: 4.3685. Min Act: -0.1700
Data Index: 510635 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19