Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.8227. Min Act: -0.1700
Data Index: 411340 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.8227. Min Act: -0.1700
Data Index: 2307930 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.7915. Min Act: -0.1700
Data Index: 3042565 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.7602. Min Act: -0.1700
Data Index: 4284483 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6977. Min Act: -0.1700
Data Index: 8789342 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6665. Min Act: -0.1700
Data Index: 2739971 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6665. Min Act: -0.1700
Data Index: 2948174 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6665. Min Act: -0.1700
Data Index: 3742442 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6665. Min Act: -0.1700
Data Index: 7994144 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 7162125 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6665. Min Act: -0.1700
Data Index: 2077248 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 6715610 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 1766655 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 2526328 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 7112983 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6040. Min Act: -0.1700
Data Index: 4887557 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 6903912 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 1471268 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6040. Min Act: -0.1700
Data Index: 2101119 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8227. Min Range: -4.8227
Max Act: 4.6352. Min Act: -0.1700
Data Index: 4264647 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19