Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3155. Min Range: -6.3155
Max Act: 6.3155. Min Act: -0.1700
Data Index: 2913656 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3155. Min Range: -6.3155
Max Act: 6.0967. Min Act: -0.1700
Data Index: 2788768 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.9717. Min Act: -0.1700
Data Index: 3156003 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.9405. Min Act: -0.1700
Data Index: 6978940 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.9405. Min Act: -0.1700
Data Index: 4545381 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.9405. Min Act: -0.1700
Data Index: 3209524 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8467. Min Act: -0.1700
Data Index: 6907978 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8467. Min Act: -0.1700
Data Index: 4649226 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2643488 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8155. Min Act: -0.1700
Data Index: 1796411 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8155. Min Act: -0.1700
Data Index: 2711292 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.8155. Min Act: -0.1700
Data Index: 6342358 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7842. Min Act: -0.1700
Data Index: 3662932 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7530. Min Act: -0.1700
Data Index: 7243389 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7842. Min Act: -0.1700
Data Index: 1065422 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7842. Min Act: -0.1700
Data Index: 4801386 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7530. Min Act: -0.1700
Data Index: 3664591 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7530. Min Act: -0.1700
Data Index: 1711686 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.7530. Min Act: -0.1700
Data Index: 5612918 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3155. Min Range: -6.3155
Max Act: 5.6905. Min Act: -0.1700
Data Index: 664114 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19