Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6109. Min Range: -7.6109
Max Act: 7.6109. Min Act: -0.1700
Data Index: 4032137 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.7359. Min Act: -0.1700
Data Index: 7480125 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.7047. Min Act: -0.1700
Data Index: 5470076 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.6422. Min Act: -0.1700
Data Index: 2861187 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.6109. Min Act: -0.1700
Data Index: 31526 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.6109. Min Act: -0.1700
Data Index: 5963549 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.5484. Min Act: -0.1700
Data Index: 5088623 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.4859. Min Act: -0.1700
Data Index: 7185921 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.4547. Min Act: -0.1700
Data Index: 5971153 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.4859. Min Act: -0.1700
Data Index: 1767613 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.4547. Min Act: -0.1700
Data Index: 233453 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.4234. Min Act: -0.1700
Data Index: 1280504 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3609. Min Act: -0.1700
Data Index: 1222167 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3609. Min Act: -0.1700
Data Index: 938991 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3609. Min Act: -0.1700
Data Index: 6343945 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3609. Min Act: -0.1700
Data Index: 715756 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3609. Min Act: -0.1700
Data Index: 6973148 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3297. Min Act: -0.1700
Data Index: 6741821 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.3297. Min Act: -0.1700
Data Index: 3450462 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6109. Min Range: -7.6109
Max Act: 6.2984. Min Act: -0.1700
Data Index: 3842483 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19