Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2216. Min Range: -8.2216
Max Act: 8.2216. Min Act: -0.1700
Data Index: 8740876 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2216. Min Range: -8.2216
Max Act: 8.1591. Min Act: -0.1700
Data Index: 2716094 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.9091. Min Act: -0.1700
Data Index: 5990054 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8778. Min Act: -0.1700
Data Index: 8487978 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8466. Min Act: -0.1700
Data Index: 7165417 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8466. Min Act: -0.1700
Data Index: 3784501 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8466. Min Act: -0.1700
Data Index: 7447613 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8466. Min Act: -0.1700
Data Index: 8240634 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.8153. Min Act: -0.1700
Data Index: 1005167 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7528. Min Act: -0.1700
Data Index: 7051308 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 4486760 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 3010688 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 5636279 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.6903. Min Act: -0.1700
Data Index: 2134559 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 8128184 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 3146919 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.7528. Min Act: -0.1700
Data Index: 1382383 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.6591. Min Act: -0.1700
Data Index: 4029672 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.6591. Min Act: -0.1700
Data Index: 6641609 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2216. Min Range: -8.2216
Max Act: 7.6278. Min Act: -0.1700
Data Index: 4184642 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19