Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.9140. Min Act: -0.1700
Data Index: 2590634 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.8515. Min Act: -0.1700
Data Index: 8135470 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.6640. Min Act: -0.1700
Data Index: 3308014 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.6640. Min Act: -0.1700
Data Index: 5749759 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.7265. Min Act: -0.1700
Data Index: 1228229 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.6640. Min Act: -0.1700
Data Index: 2861461 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.6015. Min Act: -0.1700
Data Index: 3888691 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.6015. Min Act: -0.1700
Data Index: 6035564 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4765. Min Act: -0.1700
Data Index: 6235150 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.5390. Min Act: -0.1700
Data Index: 4085571 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.5390. Min Act: -0.1700
Data Index: 1444603 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4765. Min Act: -0.1700
Data Index: 6377412 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4765. Min Act: -0.1700
Data Index: 3679178 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4765. Min Act: -0.1700
Data Index: 1265007 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 1155878 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 3993863 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 4185425 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 6611147 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 6017064 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9140. Min Range: -9.9140
Max Act: 9.4140. Min Act: -0.1700
Data Index: 2253146 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19