Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.4026. Min Range: -11.4026
Max Act: 11.4026. Min Act: -0.1700
Data Index: 3778850 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4026. Min Range: -11.4026
Max Act: 11.2776. Min Act: -0.1700
Data Index: 3440823 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4026. Min Range: -11.4026
Max Act: 11.2151. Min Act: -0.1700
Data Index: 693493 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4026. Min Range: -11.4026
Max Act: 11.1526. Min Act: -0.1698
Data Index: 811906 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4026. Min Range: -11.4026
Max Act: 11.0276. Min Act: -0.1691
Data Index: 1470078 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.9026. Min Act: -0.1663
Data Index: 1821338 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.7776. Min Act: -0.1700
Data Index: 2657593 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.6526. Min Act: -0.1700
Data Index: 4070854 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.6526. Min Act: -0.1700
Data Index: 1505660 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.6526. Min Act: -0.1696
Data Index: 4179587 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.6526. Min Act: -0.1700
Data Index: 6001914 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.5901. Min Act: -0.1699
Data Index: 3330424 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.5901. Min Act: -0.1693
Data Index: 5187288 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.6526. Min Act: -0.1700
Data Index: 7649367 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.4651. Min Act: -0.1700
Data Index: 4899181 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.5276. Min Act: -0.1698
Data Index: 2160884 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.5276. Min Act: -0.1699
Data Index: 56975 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.4651. Min Act: -0.1700
Data Index: 2177486 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.4651. Min Act: -0.1700
Data Index: 4957349 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4026. Min Range: -11.4026
Max Act: 10.5276. Min Act: -0.1700
Data Index: 6804161 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19