Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.8240. Min Act: -0.1700
Data Index: 256263 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5591386 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1474334 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 8047933 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 6760454 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4178. Min Act: -0.1700
Data Index: 5641479 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 3305134 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 7175720 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4178. Min Act: -0.1700
Data Index: 6516936 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 1874185 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3865. Min Act: -0.1700
Data Index: 2109701 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3865. Min Act: -0.1700
Data Index: 5359960 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3553. Min Act: -0.1700
Data Index: 2379 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.3240. Min Act: -0.1700
Data Index: 3199900 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 2727357 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 2863234 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 3657818 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2615. Min Act: -0.1700
Data Index: 3981728 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2928. Min Act: -0.1700
Data Index: 5017580 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.2615. Min Act: -0.1700
Data Index: 7974958 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19