Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.3404. Min Act: -0.1700
Data Index: 1063257 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3404. Min Range: -5.3404
Max Act: 5.0904. Min Act: -0.1700
Data Index: 2555770 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.6529. Min Act: -0.1700
Data Index: 8284443 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.3716. Min Act: -0.1700
Data Index: 3931453 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.4341. Min Act: -0.1700
Data Index: 2138763 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.4029. Min Act: -0.1700
Data Index: 7519233 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.3403. Min Act: -0.1700
Data Index: 26801 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.3716. Min Act: -0.1700
Data Index: 439586 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.3403. Min Act: -0.1700
Data Index: 7235446 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.4029. Min Act: -0.1700
Data Index: 8498147 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.3091. Min Act: -0.1700
Data Index: 1648327 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1841. Min Act: -0.1700
Data Index: 6641655 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.2466. Min Act: -0.1700
Data Index: 7076192 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1841. Min Act: -0.1700
Data Index: 4314507 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.2466. Min Act: -0.1700
Data Index: 6120082 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1534620 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1528. Min Act: -0.1700
Data Index: 3459289 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1841. Min Act: -0.1700
Data Index: 4186134 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1841. Min Act: -0.1700
Data Index: 201557 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3404. Min Range: -5.3404
Max Act: 4.1528. Min Act: -0.1700
Data Index: 4018003 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19