Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.9609. Min Act: -0.1700
Data Index: 6683071 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.3359. Min Act: -0.1700
Data Index: 476878 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.2734. Min Act: -0.1700
Data Index: 781369 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.0859. Min Act: -0.1700
Data Index: 4786661 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.0859. Min Act: -0.1700
Data Index: 7881777 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.0859. Min Act: -0.1700
Data Index: 757575 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9609. Min Range: -9.9609
Max Act: 9.0234. Min Act: -0.1700
Data Index: 64538 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.9609. Min Act: -0.1700
Data Index: 2506450 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.8984. Min Act: -0.1700
Data Index: 5209937 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.7734. Min Act: -0.1700
Data Index: 1084029 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.8359. Min Act: -0.1700
Data Index: 489318 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.8359. Min Act: -0.1700
Data Index: 4230697 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.7109. Min Act: -0.1700
Data Index: 4666769 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.7734. Min Act: -0.1700
Data Index: 1828314 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.6484. Min Act: -0.1700
Data Index: 696643 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.6484. Min Act: -0.1700
Data Index: 806168 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.6484. Min Act: -0.1700
Data Index: 7710205 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.7109. Min Act: -0.1700
Data Index: 6898153 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.5859. Min Act: -0.1700
Data Index: 3698418 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9609. Min Range: -9.9609
Max Act: 8.5859. Min Act: -0.1700
Data Index: 1080069 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19