Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.9425. Min Act: -0.1700
Data Index: 6652952 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.9113. Min Act: -0.1700
Data Index: 6714940 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.8175. Min Act: -0.1700
Data Index: 7128252 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.7863. Min Act: -0.1700
Data Index: 1409957 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.7550. Min Act: -0.1700
Data Index: 195539 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.7550. Min Act: -0.1700
Data Index: 7410160 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.7238. Min Act: -0.1700
Data Index: 665568 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.7238. Min Act: -0.1700
Data Index: 508658 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.6925. Min Act: -0.1700
Data Index: 5333580 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.6613. Min Act: -0.1700
Data Index: 3471147 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.6613. Min Act: -0.1700
Data Index: 7619166 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.6300. Min Act: -0.1700
Data Index: 45814 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.6300. Min Act: -0.1700
Data Index: 7517907 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1183137 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 7273006 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 2445562 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 5663946 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 4101365 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5988. Min Act: -0.1700
Data Index: 6190474 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9425. Min Range: -5.9425
Max Act: 5.5675. Min Act: -0.1700
Data Index: 358609 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19