Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2221. Min Range: -6.2221
Max Act: 6.2221. Min Act: -0.1700
Data Index: 8711773 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.9096. Min Act: -0.1700
Data Index: 7060300 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.8471. Min Act: -0.1700
Data Index: 8813631 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.7221. Min Act: -0.1700
Data Index: 2527349 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6908. Min Act: -0.1700
Data Index: 5569809 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7399466 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6596. Min Act: -0.1700
Data Index: 2580357 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6596. Min Act: -0.1700
Data Index: 1044614 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3062156 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3248205 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.6283. Min Act: -0.1700
Data Index: 5190155 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5851228 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5971. Min Act: -0.1700
Data Index: 7357689 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5658. Min Act: -0.1700
Data Index: 7537650 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5658. Min Act: -0.1700
Data Index: 4693936 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5658. Min Act: -0.1700
Data Index: 6196860 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5346. Min Act: -0.1700
Data Index: 7916907 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5346. Min Act: -0.1700
Data Index: 8666972 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5346. Min Act: -0.1700
Data Index: 3989253 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2221. Min Range: -6.2221
Max Act: 5.5033. Min Act: -0.1700
Data Index: 7559387 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19