Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1510 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.5210. Min Act: -0.1700
Data Index: 5164674 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.3960. Min Act: -0.1700
Data Index: 1870716 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.3335. Min Act: -0.1700
Data Index: 3167578 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.3335. Min Act: -0.1700
Data Index: 4762324 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.3022. Min Act: -0.1700
Data Index: 8521467 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.3022. Min Act: -0.1700
Data Index: 7477116 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2709. Min Act: -0.1700
Data Index: 6927954 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2709. Min Act: -0.1700
Data Index: 6945181 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2709. Min Act: -0.1700
Data Index: 900802 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 7814736 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 2442508 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 6073469 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 3084746 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 5711358 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.2084. Min Act: -0.1700
Data Index: 3760259 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.1772. Min Act: -0.1700
Data Index: 375590 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.1772. Min Act: -0.1700
Data Index: 4209132 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.1772. Min Act: -0.1700
Data Index: 4914184 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.1772. Min Act: -0.1700
Data Index: 1838113 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5210. Min Range: -4.5210
Max Act: 4.1772. Min Act: -0.1700
Data Index: 963620 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19