Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.9497. Min Act: -0.1700
Data Index: 8033073 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.8559. Min Act: -0.1700
Data Index: 8226595 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7933. Min Act: -0.1700
Data Index: 72313 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7620. Min Act: -0.1700
Data Index: 2413138 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7933. Min Act: -0.1700
Data Index: 2160868 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7620. Min Act: -0.1700
Data Index: 5425948 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7620. Min Act: -0.1700
Data Index: 615543 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7308. Min Act: -0.1700
Data Index: 2822527 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.7620. Min Act: -0.1700
Data Index: 7368740 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6995. Min Act: -0.1700
Data Index: 5278814 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6995. Min Act: -0.1700
Data Index: 2584827 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6682. Min Act: -0.1700
Data Index: 7615068 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6682. Min Act: -0.1700
Data Index: 1778757 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6682. Min Act: -0.1700
Data Index: 2424289 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6369. Min Act: -0.1700
Data Index: 4871421 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6056. Min Act: -0.1700
Data Index: 5510197 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6056. Min Act: -0.1700
Data Index: 4035322 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6369. Min Act: -0.1700
Data Index: 87405 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6369. Min Act: -0.1700
Data Index: 3582695 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9497. Min Range: -3.9497
Max Act: 3.6056. Min Act: -0.1700
Data Index: 6549827 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19