Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.3321. Min Act: -0.1700
Data Index: 3607361 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.3008. Min Act: -0.1700
Data Index: 8768110 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.1446. Min Act: -0.1700
Data Index: 6644918 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.1446. Min Act: -0.1700
Data Index: 6489247 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.1133. Min Act: -0.1700
Data Index: 6751951 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.1133. Min Act: -0.1700
Data Index: 8128459 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.0821. Min Act: -0.1700
Data Index: 1519470 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.0821. Min Act: -0.1700
Data Index: 1991184 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.0508. Min Act: -0.1700
Data Index: 6796392 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.0508. Min Act: -0.1700
Data Index: 3745445 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9883. Min Act: -0.1700
Data Index: 6205869 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3321. Min Range: -7.3321
Max Act: 7.0196. Min Act: -0.1700
Data Index: 7692479 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9883. Min Act: -0.1700
Data Index: 4385684 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9571. Min Act: -0.1700
Data Index: 2889106 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9571. Min Act: -0.1700
Data Index: 7085788 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9258. Min Act: -0.1700
Data Index: 1168665 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9258. Min Act: -0.1700
Data Index: 7805396 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9571. Min Act: -0.1700
Data Index: 5853594 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.9258. Min Act: -0.1700
Data Index: 985671 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3321. Min Range: -7.3321
Max Act: 6.8946. Min Act: -0.1700
Data Index: 5598504 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19