Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4731 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.7217. Min Act: -0.1700
Data Index: 5138020 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.5655. Min Act: -0.1700
Data Index: 816913 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.4717. Min Act: -0.1700
Data Index: 4911259 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.3780. Min Act: -0.1700
Data Index: 784883 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.3780. Min Act: -0.1700
Data Index: 1749780 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.3780. Min Act: -0.1700
Data Index: 4879861 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.3467. Min Act: -0.1700
Data Index: 484411 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2530. Min Act: -0.1700
Data Index: 5589829 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2530. Min Act: -0.1700
Data Index: 8683140 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 1997570 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 518471 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 3254610 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.1905. Min Act: -0.1700
Data Index: 829343 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.2217. Min Act: -0.1700
Data Index: 133977 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 3015321 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.1280. Min Act: -0.1700
Data Index: 1444541 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.0967. Min Act: -0.1700
Data Index: 2543849 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.0967. Min Act: -0.1700
Data Index: 4723496 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 1853419 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7217. Min Range: -6.7217
Max Act: 6.0655. Min Act: -0.1700
Data Index: 6679948 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19