Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1307 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.2204. Min Act: -0.1700
Data Index: 4267293 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.1267. Min Act: -0.1700
Data Index: 2275091 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.1267. Min Act: -0.1700
Data Index: 4516391 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0642. Min Act: -0.1700
Data Index: 44359 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0954. Min Act: -0.1700
Data Index: 7061638 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0954. Min Act: -0.1700
Data Index: 60772 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0642. Min Act: -0.1700
Data Index: 1191158 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0017. Min Act: -0.1700
Data Index: 6549529 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0329. Min Act: -0.1700
Data Index: 3509368 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0017. Min Act: -0.1700
Data Index: 7571216 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2204. Min Range: -5.2204
Max Act: 5.0017. Min Act: -0.1700
Data Index: 1577872 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9704. Min Act: -0.1700
Data Index: 5320005 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9704. Min Act: -0.1700
Data Index: 168403 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9704. Min Act: -0.1700
Data Index: 4936559 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9704. Min Act: -0.1700
Data Index: 733286 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9079. Min Act: -0.1700
Data Index: 6451362 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.8767. Min Act: -0.1700
Data Index: 1073552 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9079. Min Act: -0.1700
Data Index: 419850 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.9079. Min Act: -0.1700
Data Index: 2755005 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2204. Min Range: -5.2204
Max Act: 4.8767. Min Act: -0.1700
Data Index: 1675852 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19