Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 208 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6834. Min Act: -0.0000

Data Index: 429938 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6968. Min Act: -0.0000

Data Index: 187796 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6606. Min Act: -0.0000

Data Index: 494740 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6646. Min Act: -0.0000

Data Index: 545679 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5853. Min Act: -0.0000

Data Index: 462660 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1243746 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1361167 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1355947 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1524808 (Python Code)

Max Activating Token Index: 359

Text #9

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5629. Min Act: -0.0000

Data Index: 975974 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1470305 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1367386 (Python Code)

Max Activating Token Index: 630

Text #12

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5491. Min Act: -0.0000

Data Index: 720674 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5239. Min Act: -0.0000

Data Index: 748175 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5269. Min Act: -0.0000

Data Index: 350044 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1251169 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1341375 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5280. Min Act: 0.0000

Data Index: 573089 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1652461 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.4625. Min Act: -0.0000

Data Index: 490324 (C4 (Web Text))

Max Activating Token Index: 705