Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2309. Min Range: -6.2309
Max Act: 6.2309. Min Act: -0.1700
Data Index: 5767033 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2309. Min Range: -6.2309
Max Act: 6.0434. Min Act: -0.1700
Data Index: 1449987 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2309. Min Range: -6.2309
Max Act: 6.0122. Min Act: -0.1700
Data Index: 4593038 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.9497. Min Act: -0.1700
Data Index: 7922751 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.9184. Min Act: -0.1700
Data Index: 2543342 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8872. Min Act: -0.1700
Data Index: 8379139 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8872. Min Act: -0.1700
Data Index: 4391984 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 1700844 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 2919365 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8872. Min Act: -0.1700
Data Index: 5787537 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 7656006 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 2684631 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 7268420 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8872. Min Act: -0.1700
Data Index: 1367660 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8247. Min Act: -0.1700
Data Index: 7644252 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 327778 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8247. Min Act: -0.1700
Data Index: 5308930 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 1328729 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.8559. Min Act: -0.1700
Data Index: 1452957 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2309. Min Range: -6.2309
Max Act: 5.7934. Min Act: -0.1700
Data Index: 3324684 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19