Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 38353 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2458. Min Act: -0.1700
Data Index: 7560030 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.2146. Min Act: -0.1700
Data Index: 8493267 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.1208. Min Act: -0.1700
Data Index: 5597029 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.0896. Min Act: -0.1700
Data Index: 5481250 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2458. Min Range: -5.2458
Max Act: 5.0271. Min Act: -0.1700
Data Index: 2464649 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9958. Min Act: -0.1700
Data Index: 835262 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9646. Min Act: -0.1700
Data Index: 4744873 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9646. Min Act: -0.1700
Data Index: 1311321 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9646. Min Act: -0.1700
Data Index: 1635935 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9646. Min Act: -0.1700
Data Index: 6665844 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9646. Min Act: -0.1700
Data Index: 5904370 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9021. Min Act: -0.1700
Data Index: 2142846 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9021. Min Act: -0.1700
Data Index: 8399053 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9021. Min Act: -0.1700
Data Index: 77135 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.9021. Min Act: -0.1700
Data Index: 1639540 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.8708. Min Act: -0.1700
Data Index: 3982202 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.8708. Min Act: -0.1700
Data Index: 6968342 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.8396. Min Act: -0.1700
Data Index: 6833912 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2458. Min Range: -5.2458
Max Act: 4.8396. Min Act: -0.1700
Data Index: 2412903 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19