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

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

Neuron 3112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1346054 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2283. Min Act: -0.0000

Data Index: 739108 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2146. Min Act: -0.0000

Data Index: 656446 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1932. Min Act: -0.0000

Data Index: 957037 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1947. Min Act: -0.0000

Data Index: 743809 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1894. Min Act: -0.0000

Data Index: 274906 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.2015. Min Act: -0.0000

Data Index: 717976 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1067112 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1250814 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1758. Min Act: -0.0000

Data Index: 223529 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1750. Min Act: -0.0000

Data Index: 946925 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1667. Min Act: -0.0000

Data Index: 479086 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1735. Min Act: -0.0000

Data Index: 909734 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1200400 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1836. Min Act: -0.0000

Data Index: 920101 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1072178 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1774. Min Act: -0.0000

Data Index: 285485 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1686. Min Act: -0.0000

Data Index: 428981 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1760. Min Act: -0.0000

Data Index: 958233 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.2395. Min Range: -0.2395

Max Act: 0.1613. Min Act: -0.0000

Data Index: 367961 (C4 (Web Text))

Max Activating Token Index: 902