Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.9943. Min Act: -0.1700
Data Index: 88251 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.8693. Min Act: -0.1700
Data Index: 4593753 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.6505. Min Act: -0.1700
Data Index: 5533659 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.6505. Min Act: -0.1700
Data Index: 6515052 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.5880. Min Act: -0.1700
Data Index: 4211657 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.5880. Min Act: -0.1700
Data Index: 3465799 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.5568. Min Act: -0.1700
Data Index: 6247542 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4943. Min Act: -0.1700
Data Index: 4259185 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4630. Min Act: -0.1700
Data Index: 2124252 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4630. Min Act: -0.1700
Data Index: 1459745 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4630. Min Act: -0.1700
Data Index: 3578907 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4630. Min Act: -0.1700
Data Index: 3142204 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4318. Min Act: -0.1700
Data Index: 8393850 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4318. Min Act: -0.1700
Data Index: 1298720 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4005. Min Act: -0.1700
Data Index: 7995571 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.4005. Min Act: -0.1700
Data Index: 4139456 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.3693. Min Act: -0.1700
Data Index: 7232023 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.3693. Min Act: -0.1700
Data Index: 4986048 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.3693. Min Act: -0.1700
Data Index: 6417060 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9943. Min Range: -6.9943
Max Act: 6.3380. Min Act: -0.1700
Data Index: 2509486 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19