Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1579 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.4334. Min Act: -0.1700
Data Index: 4649594 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.4022. Min Act: -0.1700
Data Index: 7125696 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.3397. Min Act: -0.1700
Data Index: 4735171 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.3397. Min Act: -0.1700
Data Index: 528812 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.2459. Min Act: -0.1700
Data Index: 4509830 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.2772. Min Act: -0.1700
Data Index: 92764 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.2459. Min Act: -0.1700
Data Index: 3321268 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1834. Min Act: -0.1700
Data Index: 3071837 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1834. Min Act: -0.1700
Data Index: 8176281 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1834. Min Act: -0.1700
Data Index: 7789611 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1522. Min Act: -0.1700
Data Index: 3944050 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1209. Min Act: -0.1700
Data Index: 3340562 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.1209. Min Act: -0.1700
Data Index: 7789620 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.0584. Min Act: -0.1700
Data Index: 5550426 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6721128 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4334. Min Range: -6.4334
Max Act: 6.0584. Min Act: -0.1700
Data Index: 4502180 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4334. Min Range: -6.4334
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3227363 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4334. Min Range: -6.4334
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3962105 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4334. Min Range: -6.4334
Max Act: 5.9647. Min Act: -0.1700
Data Index: 1169812 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4334. Min Range: -6.4334
Max Act: 5.9647. Min Act: -0.1700
Data Index: 7164572 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19