Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7357. Min Range: -6.7357
Max Act: 6.7357. Min Act: -0.1700
Data Index: 7611917 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.9545. Min Act: -0.1700
Data Index: 3467482 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.8920. Min Act: -0.1700
Data Index: 2957594 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.8607. Min Act: -0.1700
Data Index: 7959355 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.8295. Min Act: -0.1700
Data Index: 3517668 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7670. Min Act: -0.1700
Data Index: 3885559 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7357. Min Act: -0.1700
Data Index: 7706714 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7045. Min Act: -0.1700
Data Index: 5968837 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7045. Min Act: -0.1700
Data Index: 6801589 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7045. Min Act: -0.1700
Data Index: 2277422 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.7045. Min Act: -0.1700
Data Index: 7605054 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 874007 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6732. Min Act: -0.1700
Data Index: 5026168 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 8047718 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6732. Min Act: -0.1700
Data Index: 5359421 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 3788246 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 4571460 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 7732697 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6420. Min Act: -0.1700
Data Index: 418291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7357. Min Range: -6.7357
Max Act: 5.6107. Min Act: -0.1700
Data Index: 2344976 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19