Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.2781. Min Act: -0.1700
Data Index: 6242054 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.2469. Min Act: -0.1700
Data Index: 6234698 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.2156. Min Act: -0.1700
Data Index: 941632 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.1844. Min Act: -0.1700
Data Index: 6911885 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.1531. Min Act: -0.1700
Data Index: 2895698 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3541857 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.1219. Min Act: -0.1700
Data Index: 5274175 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.1219. Min Act: -0.1700
Data Index: 7809640 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.0594. Min Act: -0.1700
Data Index: 2268633 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2781. Min Range: -6.2781
Max Act: 6.0281. Min Act: -0.1700
Data Index: 651093 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9969. Min Act: -0.1700
Data Index: 3879388 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9969. Min Act: -0.1700
Data Index: 4584048 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 5607060 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 1012866 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 5861849 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 8406832 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 4077836 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9031. Min Act: -0.1700
Data Index: 3579821 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9344. Min Act: -0.1700
Data Index: 60618 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2781. Min Range: -6.2781
Max Act: 5.9656. Min Act: -0.1700
Data Index: 7416976 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19