Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.2355. Min Act: -0.1700
Data Index: 5295095 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1418. Min Act: -0.1700
Data Index: 8579538 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.1418. Min Act: -0.1700
Data Index: 5084635 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.0480. Min Act: -0.1700
Data Index: 3594852 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2355. Min Range: -4.2355
Max Act: 4.0480. Min Act: -0.1700
Data Index: 7231476 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9855. Min Act: -0.1700
Data Index: 5835661 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9855. Min Act: -0.1700
Data Index: 8200021 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9855. Min Act: -0.1700
Data Index: 3448591 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9855. Min Act: -0.1700
Data Index: 4219024 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 1201913 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 328262 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 3365470 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 6706289 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 7485402 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 4067868 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 7848225 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 7854742 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.9542. Min Act: -0.1700
Data Index: 2305567 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.8917. Min Act: -0.1700
Data Index: 6843594 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2355. Min Range: -4.2355
Max Act: 3.8917. Min Act: -0.1700
Data Index: 357492 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19