Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.4611. Min Act: -0.1700
Data Index: 4546990 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4611. Min Range: -7.4611
Max Act: 7.2111. Min Act: -0.1700
Data Index: 7109470 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.9923. Min Act: -0.1700
Data Index: 2721883 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8986. Min Act: -0.1700
Data Index: 4495820 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.9298. Min Act: -0.1700
Data Index: 6977280 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8673. Min Act: -0.1700
Data Index: 7909988 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8673. Min Act: -0.1700
Data Index: 2724039 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.8361. Min Act: -0.1700
Data Index: 5296119 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7736. Min Act: -0.1700
Data Index: 5812742 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7423. Min Act: -0.1700
Data Index: 2394574 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7736. Min Act: -0.1700
Data Index: 4284399 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7423. Min Act: -0.1700
Data Index: 8822554 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7423. Min Act: -0.1700
Data Index: 1999984 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.7111. Min Act: -0.1700
Data Index: 355933 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6798. Min Act: -0.1700
Data Index: 32326 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 1040621 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 5023730 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 2412512 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6173. Min Act: -0.1700
Data Index: 1458020 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4611. Min Range: -7.4611
Max Act: 6.6486. Min Act: -0.1700
Data Index: 4187655 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19