Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.7684. Min Act: -0.1700
Data Index: 4703681 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.7059. Min Act: -0.1700
Data Index: 5572580 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.7059. Min Act: -0.1700
Data Index: 5324003 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.6434. Min Act: -0.1700
Data Index: 7539819 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.6434. Min Act: -0.1700
Data Index: 6807458 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 7261383 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.6122. Min Act: -0.1700
Data Index: 8235191 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.5184. Min Act: -0.1700
Data Index: 7999672 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4872. Min Act: -0.1700
Data Index: 664804 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4559. Min Act: -0.1700
Data Index: 8648105 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4559. Min Act: -0.1700
Data Index: 1390960 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4872. Min Act: -0.1700
Data Index: 7094361 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4247. Min Act: -0.1700
Data Index: 6670268 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4559. Min Act: -0.1700
Data Index: 6544866 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4247. Min Act: -0.1700
Data Index: 3978939 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.4247. Min Act: -0.1700
Data Index: 5865866 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.3934. Min Act: -0.1700
Data Index: 4040082 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.3934. Min Act: -0.1700
Data Index: 8058427 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.3622. Min Act: -0.1700
Data Index: 6937765 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7684. Min Range: -6.7684
Max Act: 6.3309. Min Act: -0.1700
Data Index: 8451180 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19