Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.8061. Min Act: -0.1700
Data Index: 267459 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.7436. Min Act: -0.1700
Data Index: 4566421 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.6498. Min Act: -0.1700
Data Index: 7302755 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.6186. Min Act: -0.1700
Data Index: 3758764 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.6186. Min Act: -0.1700
Data Index: 5749087 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.6186. Min Act: -0.1700
Data Index: 3983372 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7210285 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.5248. Min Act: -0.1700
Data Index: 4396594 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.5248. Min Act: -0.1700
Data Index: 1487413 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4936. Min Act: -0.1700
Data Index: 5749096 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3903760 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4936. Min Act: -0.1700
Data Index: 8638400 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4623. Min Act: -0.1700
Data Index: 1730580 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4623. Min Act: -0.1700
Data Index: 7210284 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.4311. Min Act: -0.1700
Data Index: 402639 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.3998. Min Act: -0.1700
Data Index: 8232275 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.3998. Min Act: -0.1700
Data Index: 243824 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.3373. Min Act: -0.1700
Data Index: 5492765 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.3686. Min Act: -0.1700
Data Index: 7092024 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8061. Min Range: -5.8061
Max Act: 5.3061. Min Act: -0.1700
Data Index: 7053627 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19