Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4731. Min Act: -0.1700
Data Index: 5667530 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4731. Min Act: -0.1700
Data Index: 4928362 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.5043. Min Act: -0.1700
Data Index: 2166191 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4731. Min Act: -0.1700
Data Index: 6459865 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4418. Min Act: -0.1700
Data Index: 1551743 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4418. Min Act: -0.1700
Data Index: 908296 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4418. Min Act: -0.1700
Data Index: 8708475 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.4106. Min Act: -0.1700
Data Index: 357173 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 8184930 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 6851391 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 1275021 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 4581645 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3481. Min Act: -0.1700
Data Index: 2561574 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 5032105 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 5047413 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 8503209 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3481. Min Act: -0.1700
Data Index: 7574341 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3481. Min Act: -0.1700
Data Index: 4212409 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3793. Min Act: -0.1700
Data Index: 7797421 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5043. Min Range: -5.5043
Max Act: 5.3481. Min Act: -0.1700
Data Index: 7804192 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19