Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5935 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.8861. Min Act: -0.0000

Data Index: 768270 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1060980 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.9337. Min Act: -0.0000

Data Index: 1251849 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.7131. Min Act: -0.0000

Data Index: 573956 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.8732. Min Act: -0.0000

Data Index: 98808 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.8802. Min Act: -0.0000

Data Index: 146705 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.7630. Min Act: -0.0000

Data Index: 1000758 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.8384. Min Act: -0.0000

Data Index: 1023204 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.8239. Min Act: -0.0000

Data Index: 639595 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1114375 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1178203 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.7536. Min Act: -0.0000

Data Index: 502459 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6518. Min Act: 0.0000

Data Index: 951761 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.7314. Min Act: -0.0000

Data Index: 436995 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6361. Min Act: -0.0000

Data Index: 472979 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6307. Min Act: -0.0000

Data Index: 932042 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6214. Min Act: -0.0000

Data Index: 81427 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6021. Min Act: -0.0000

Data Index: 113458 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.6011. Min Act: -0.0000

Data Index: 542443 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.9442. Min Range: -1.9442

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1003723 (C4 (Web Text))

Max Activating Token Index: 813