Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.8446. Min Act: -0.1700
Data Index: 1392645 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.7821. Min Act: -0.1700
Data Index: 8804645 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.7821. Min Act: -0.1699
Data Index: 5655943 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.7196. Min Act: -0.1698
Data Index: 4974007 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.5946. Min Act: -0.1698
Data Index: 3828178 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.5321. Min Act: -0.1700
Data Index: 5527371 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.5321. Min Act: -0.1700
Data Index: 1977305 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.5321. Min Act: -0.1700
Data Index: 1032692 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.4071. Min Act: -0.1696
Data Index: 5101446 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.4071. Min Act: -0.1700
Data Index: 1032694 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.2821. Min Act: -0.1695
Data Index: 1032693 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.2821. Min Act: -0.1700
Data Index: 3243842 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.1571. Min Act: -0.1698
Data Index: 4131922 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0946. Min Act: -0.1700
Data Index: 1032697 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0321. Min Act: -0.1700
Data Index: 3221931 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0321. Min Act: -0.1700
Data Index: 1048200 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0946. Min Act: -0.1698
Data Index: 6417027 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0321. Min Act: -0.1700
Data Index: 4781076 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0321. Min Act: -0.1700
Data Index: 521435 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8446. Min Range: -9.8446
Max Act: 9.0321. Min Act: -0.1700
Data Index: 3613184 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19