Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1234. Min Range: -7.1234
Max Act: 7.1234. Min Act: -0.1700
Data Index: 956410 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.8422. Min Act: -0.1700
Data Index: 2145796 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.8109. Min Act: -0.1700
Data Index: 7709888 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.7797. Min Act: -0.1700
Data Index: 1821132 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.7797. Min Act: -0.1700
Data Index: 7294401 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.6859. Min Act: -0.1700
Data Index: 2245182 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.6859. Min Act: -0.1700
Data Index: 8756232 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.7172. Min Act: -0.1700
Data Index: 3498058 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.6859. Min Act: -0.1700
Data Index: 5177239 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.6547. Min Act: -0.1700
Data Index: 3193051 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.6234. Min Act: -0.1700
Data Index: 6330110 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5922. Min Act: -0.1700
Data Index: 7093023 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5609. Min Act: -0.1700
Data Index: 6384847 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5609. Min Act: -0.1700
Data Index: 5002769 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5609. Min Act: -0.1700
Data Index: 156343 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.4984. Min Act: -0.1700
Data Index: 3912860 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5297. Min Act: -0.1700
Data Index: 7614837 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5297. Min Act: -0.1700
Data Index: 6611309 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.5609. Min Act: -0.1700
Data Index: 3027550 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1234. Min Range: -7.1234
Max Act: 6.4984. Min Act: -0.1700
Data Index: 4518543 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19