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

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

Neuron 3996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.6513. Min Act: -0.0000

Data Index: 606542 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5350. Min Act: -0.0000

Data Index: 889423 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1131004 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4702. Min Act: -0.0000

Data Index: 87020 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4916. Min Act: -0.0000

Data Index: 584496 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4692. Min Act: -0.0000

Data Index: 236543 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4473. Min Act: -0.0000

Data Index: 994328 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4772. Min Act: -0.0000

Data Index: 351599 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1042647 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4397. Min Act: -0.0000

Data Index: 766866 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1296821 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4170. Min Act: -0.0000

Data Index: 678731 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3972. Min Act: -0.0000

Data Index: 747952 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3965. Min Act: -0.0000

Data Index: 46351 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4117. Min Act: -0.0000

Data Index: 773232 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1042534 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1244215 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3773. Min Act: -0.0000

Data Index: 236237 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.4007. Min Act: -0.0000

Data Index: 430982 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.6513. Min Range: -0.6513

Max Act: 0.3879. Min Act: -0.0000

Data Index: 708220 (C4 (Web Text))

Max Activating Token Index: 532