Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.4180. Min Act: -0.1700
Data Index: 1528691 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.3853. Min Act: -0.1700
Data Index: 8277699 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.3690. Min Act: -0.1700
Data Index: 238607 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.3526. Min Act: -0.1700
Data Index: 8717465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.3362. Min Act: -0.1700
Data Index: 8005815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.3198. Min Act: -0.1700
Data Index: 7003809 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2704. Min Act: -0.1700
Data Index: 5936455 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2704. Min Act: -0.1700
Data Index: 2590942 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2704. Min Act: -0.1700
Data Index: 4893288 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2374. Min Act: -0.1700
Data Index: 2814147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1877. Min Act: -0.1700
Data Index: 8664283 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2043. Min Act: -0.1700
Data Index: 7907140 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2043. Min Act: -0.1700
Data Index: 5362362 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.2043. Min Act: -0.1700
Data Index: 6843703 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1710. Min Act: -0.1700
Data Index: 2802179 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1710. Min Act: -0.1700
Data Index: 7681880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1877. Min Act: -0.1700
Data Index: 1631956 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1877. Min Act: -0.1700
Data Index: 58446 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1710. Min Act: -0.1700
Data Index: 6561385 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4180. Min Range: -2.4180
Max Act: 2.1877. Min Act: -0.1700
Data Index: 4877870 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19