Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2176 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.3353. Min Act: -0.1700
Data Index: 1571975 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.3040. Min Act: -0.1700
Data Index: 7257500 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.3040. Min Act: -0.1700
Data Index: 6066926 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2415. Min Act: -0.1700
Data Index: 4965048 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.2415. Min Act: -0.1700
Data Index: 2526313 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.1165. Min Act: -0.1700
Data Index: 88527 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.1165. Min Act: -0.1700
Data Index: 6581900 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0852. Min Act: -0.1700
Data Index: 4967301 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0852. Min Act: -0.1700
Data Index: 7521406 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 874091 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 7860805 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 5523005 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0540. Min Act: -0.1700
Data Index: 784725 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 2869986 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 4743296 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 3471967 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 1533683 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 7090834 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3353. Min Range: -4.3353
Max Act: 4.0227. Min Act: -0.1700
Data Index: 5392548 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3353. Min Range: -4.3353
Max Act: 3.9914. Min Act: -0.1700
Data Index: 2935362 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19