Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2403. Min Range: -6.2403
Max Act: 6.2403. Min Act: -0.1700
Data Index: 5756919 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.9590. Min Act: -0.1700
Data Index: 8477634 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.9590. Min Act: -0.1700
Data Index: 2145430 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.8653. Min Act: -0.1700
Data Index: 8259402 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.8340. Min Act: -0.1700
Data Index: 3701050 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.8028. Min Act: -0.1700
Data Index: 3828566 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7715. Min Act: -0.1700
Data Index: 1414278 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7715. Min Act: -0.1700
Data Index: 8126504 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.8028. Min Act: -0.1700
Data Index: 5659834 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 6000227 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7090. Min Act: -0.1700
Data Index: 1771092 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.8028. Min Act: -0.1700
Data Index: 4237724 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 5154692 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 1214879 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7403. Min Act: -0.1700
Data Index: 325267 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7090. Min Act: -0.1700
Data Index: 5257145 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.7090. Min Act: -0.1700
Data Index: 2666193 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.6778. Min Act: -0.1700
Data Index: 1795444 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3863598 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2403. Min Range: -6.2403
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3237706 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19