Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 455 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2155. Min Range: -9.2155
Max Act: 9.2155. Min Act: -0.1700
Data Index: 8664194 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2155. Min Range: -9.2155
Max Act: 9.1530. Min Act: -0.1700
Data Index: 6250195 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2155. Min Range: -9.2155
Max Act: 9.1530. Min Act: -0.1700
Data Index: 3875902 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2155. Min Range: -9.2155
Max Act: 9.0905. Min Act: -0.1700
Data Index: 281192 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.9655. Min Act: -0.1700
Data Index: 3645412 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.9655. Min Act: -0.1700
Data Index: 1665239 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.9030. Min Act: -0.1700
Data Index: 7522099 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.9030. Min Act: -0.1700
Data Index: 8120362 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7155. Min Act: -0.1700
Data Index: 1850176 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7780. Min Act: -0.1700
Data Index: 5952200 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7780. Min Act: -0.1700
Data Index: 3986511 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7780. Min Act: -0.1700
Data Index: 7534379 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7155. Min Act: -0.1700
Data Index: 4057425 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.7155. Min Act: -0.1700
Data Index: 2772264 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.6530. Min Act: -0.1700
Data Index: 5069292 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.6530. Min Act: -0.1700
Data Index: 1185171 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.5905. Min Act: -0.1700
Data Index: 3099413 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.5905. Min Act: -0.1700
Data Index: 4310016 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.5905. Min Act: -0.1700
Data Index: 6755892 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2155. Min Range: -9.2155
Max Act: 8.5905. Min Act: -0.1700
Data Index: 1846970 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19