Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.3811. Min Act: -0.1700
Data Index: 6469845 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.3811. Min Act: -0.1700
Data Index: 4702042 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.3186. Min Act: -0.1700
Data Index: 7664736 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.3186. Min Act: -0.1700
Data Index: 1690425 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.3186. Min Act: -0.1700
Data Index: 2654984 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.2561. Min Act: -0.1700
Data Index: 8296436 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.2561. Min Act: -0.1700
Data Index: 5866452 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.2248. Min Act: -0.1700
Data Index: 4965844 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.2248. Min Act: -0.1700
Data Index: 531097 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.2561. Min Act: -0.1700
Data Index: 3682344 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1936. Min Act: -0.1700
Data Index: 7213191 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1936. Min Act: -0.1700
Data Index: 6936767 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1936. Min Act: -0.1700
Data Index: 6339284 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1936. Min Act: -0.1700
Data Index: 1428741 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 25496 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 7254322 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 2388123 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 2460894 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 8005529 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3811. Min Range: -4.3811
Max Act: 4.1623. Min Act: -0.1700
Data Index: 4877984 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19