Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1150 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.5270. Min Act: -0.1700
Data Index: 456632 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.4333. Min Act: -0.1700
Data Index: 7287078 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.4020. Min Act: -0.1700
Data Index: 5388798 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.3708. Min Act: -0.1700
Data Index: 5593982 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.3395. Min Act: -0.1700
Data Index: 7351609 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.3083. Min Act: -0.1700
Data Index: 1659194 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.1833. Min Act: -0.1700
Data Index: 5191913 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.1833. Min Act: -0.1700
Data Index: 141573 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.1520. Min Act: -0.1700
Data Index: 1127008 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0895. Min Act: -0.1700
Data Index: 8196963 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0895. Min Act: -0.1700
Data Index: 2864835 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.1208. Min Act: -0.1700
Data Index: 2027401 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0895. Min Act: -0.1700
Data Index: 8179971 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 6057126 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 1346930 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 4425720 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 5238624 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 4786160 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 7867871 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5270. Min Range: -6.5270
Max Act: 6.0583. Min Act: -0.1700
Data Index: 7619828 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19