Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.4360. Min Act: -0.1700
Data Index: 7342619 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.3423. Min Act: -0.1700
Data Index: 53752 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.3423. Min Act: -0.1700
Data Index: 7634 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.3423. Min Act: -0.1700
Data Index: 1838845 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.2485. Min Act: -0.1700
Data Index: 4710702 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.2485. Min Act: -0.1700
Data Index: 8374990 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.2485. Min Act: -0.1700
Data Index: 5088299 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1860. Min Act: -0.1700
Data Index: 1560173 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1860. Min Act: -0.1700
Data Index: 6557834 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1860. Min Act: -0.1700
Data Index: 6303812 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.2173. Min Act: -0.1700
Data Index: 1784205 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1548. Min Act: -0.1700
Data Index: 790290 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1548. Min Act: -0.1700
Data Index: 600908 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1548. Min Act: -0.1700
Data Index: 8667250 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1548. Min Act: -0.1700
Data Index: 3185883 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1235. Min Act: -0.1700
Data Index: 3803751 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1235. Min Act: -0.1700
Data Index: 4513066 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.1235. Min Act: -0.1700
Data Index: 5369263 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.0923. Min Act: -0.1700
Data Index: 6352976 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4360. Min Range: -5.4360
Max Act: 5.0923. Min Act: -0.1700
Data Index: 6948458 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19