Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.6041. Min Act: -0.1700
Data Index: 1837812 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.5103. Min Act: -0.1700
Data Index: 2932977 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4791. Min Act: -0.1700
Data Index: 7473874 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4791. Min Act: -0.1700
Data Index: 7289697 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4791. Min Act: -0.1699
Data Index: 7655849 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4478. Min Act: -0.1700
Data Index: 8088992 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4478. Min Act: -0.1700
Data Index: 1543984 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4478. Min Act: -0.1700
Data Index: 2702748 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4478. Min Act: -0.1700
Data Index: 1387474 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4166. Min Act: -0.1700
Data Index: 4027425 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.4166. Min Act: -0.1700
Data Index: 6659071 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.3541. Min Act: -0.1700
Data Index: 5258601 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.3228. Min Act: -0.1700
Data Index: 1280648 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.3228. Min Act: -0.1700
Data Index: 7759595 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.3228. Min Act: -0.1700
Data Index: 6119846 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.3228. Min Act: -0.1700
Data Index: 1839790 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.2916. Min Act: -0.1700
Data Index: 6191903 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.2916. Min Act: -0.1700
Data Index: 4978970 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.2916. Min Act: -0.1700
Data Index: 251790 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6041. Min Range: -5.6041
Max Act: 5.2603. Min Act: -0.1700
Data Index: 6768185 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19