Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 543 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0387. Min Act: -0.1700
Data Index: 6507091 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0071. Min Act: -0.1700
Data Index: 8108971 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0387. Min Range: -3.0387
Max Act: 3.0387. Min Act: -0.1700
Data Index: 2002813 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9755. Min Act: -0.1700
Data Index: 463799 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9913. Min Act: -0.1700
Data Index: 3637811 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9596. Min Act: -0.1700
Data Index: 2170281 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9596. Min Act: -0.1700
Data Index: 2170279 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9596. Min Act: -0.1700
Data Index: 2170273 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9596. Min Act: -0.1700
Data Index: 1466536 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9438. Min Act: -0.1700
Data Index: 2745859 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9438. Min Act: -0.1700
Data Index: 8832165 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9438. Min Act: -0.1700
Data Index: 784899 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9438. Min Act: -0.1700
Data Index: 5871101 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9438. Min Act: -0.1700
Data Index: 5528651 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9280. Min Act: -0.1700
Data Index: 2170277 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9121. Min Act: -0.1700
Data Index: 5922407 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9121. Min Act: -0.1700
Data Index: 4017322 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9280. Min Act: -0.1700
Data Index: 7092564 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9280. Min Act: -0.1700
Data Index: 2170293 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0387. Min Range: -3.0387
Max Act: 2.9280. Min Act: -0.1700
Data Index: 2170297 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19