Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1942 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.2707. Min Act: -0.1700
Data Index: 4667950 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.2082. Min Act: -0.1700
Data Index: 7580089 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.1769. Min Act: -0.1700
Data Index: 3691121 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.1457. Min Act: -0.1700
Data Index: 7677591 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.1144. Min Act: -0.1700
Data Index: 7128324 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.1144. Min Act: -0.1700
Data Index: 6431837 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0832. Min Act: -0.1700
Data Index: 838665 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0519. Min Act: -0.1700
Data Index: 5385110 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0519. Min Act: -0.1700
Data Index: 7429781 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0519. Min Act: -0.1700
Data Index: 5693070 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0207. Min Act: -0.1700
Data Index: 6993270 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2707. Min Range: -7.2707
Max Act: 7.0207. Min Act: -0.1699
Data Index: 5323841 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 2636202 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 4763145 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9582. Min Act: -0.1700
Data Index: 5433555 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9894. Min Act: -0.1700
Data Index: 5442475 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9582. Min Act: -0.1700
Data Index: 3313198 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 1030110 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 7516916 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2707. Min Range: -7.2707
Max Act: 6.9269. Min Act: -0.1700
Data Index: 8179970 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19