Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4961. Min Range: -8.4961
Max Act: 8.4961. Min Act: -0.1700
Data Index: 3111309 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.9336. Min Act: -0.1700
Data Index: 5854177 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.9336. Min Act: -0.1700
Data Index: 2461149 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.6211. Min Act: -0.1700
Data Index: 6639120 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.6211. Min Act: -0.1700
Data Index: 4038422 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.6211. Min Act: -0.1700
Data Index: 7175442 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.6211. Min Act: -0.1700
Data Index: 3237696 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5586. Min Act: -0.1700
Data Index: 6699095 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5274. Min Act: -0.1700
Data Index: 7999589 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5586. Min Act: -0.1700
Data Index: 251607 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5586. Min Act: -0.1700
Data Index: 7131169 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5586. Min Act: -0.1700
Data Index: 655692 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.6211. Min Act: -0.1700
Data Index: 1336079 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5274. Min Act: -0.1700
Data Index: 4040239 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.5274. Min Act: -0.1700
Data Index: 6921513 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.4961. Min Act: -0.1700
Data Index: 823886 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.4649. Min Act: -0.1700
Data Index: 600026 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.4961. Min Act: -0.1700
Data Index: 1639137 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.4961. Min Act: -0.1700
Data Index: 1919630 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4961. Min Range: -8.4961
Max Act: 7.4649. Min Act: -0.1700
Data Index: 2668767 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19