Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2187. Min Range: -7.2187
Max Act: 7.2187. Min Act: -0.1700
Data Index: 8011491 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2187. Min Range: -7.2187
Max Act: 7.0312. Min Act: -0.1700
Data Index: 6506045 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2187. Min Range: -7.2187
Max Act: 7.0000. Min Act: -0.1700
Data Index: 5310648 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.8125. Min Act: -0.1700
Data Index: 7487195 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.6875. Min Act: -0.1700
Data Index: 6521253 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.6875. Min Act: -0.1700
Data Index: 8089170 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.6250. Min Act: -0.1700
Data Index: 7878290 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.6250. Min Act: -0.1700
Data Index: 217149 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.4687. Min Act: -0.1700
Data Index: 902679 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.4062. Min Act: -0.1700
Data Index: 7065326 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.3437. Min Act: -0.1700
Data Index: 4509851 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2812. Min Act: -0.1700
Data Index: 8089172 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 120193 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2500. Min Act: -0.1700
Data Index: 4271204 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2812. Min Act: -0.1700
Data Index: 331827 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 6601277 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 2275773 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 6589795 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.2187. Min Act: -0.1700
Data Index: 2364415 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2187. Min Range: -7.2187
Max Act: 6.1875. Min Act: -0.1700
Data Index: 5061910 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19