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

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

Neuron 3040 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1497636 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1117934 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2233. Min Act: -0.0000

Data Index: 475366 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2237. Min Act: -0.0000

Data Index: 152506 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2191. Min Act: -0.0000

Data Index: 402664 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2104. Min Act: -0.0000

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1940. Min Act: -0.0000

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2090. Min Act: -0.0000

Data Index: 588929 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2041. Min Act: -0.0000

Data Index: 155888 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2088. Min Act: -0.0000

Data Index: 187330 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2030. Min Act: -0.0000

Data Index: 818762 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1881. Min Act: -0.0000

Data Index: 734436 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1968. Min Act: -0.0000

Data Index: 792551 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1901. Min Act: -0.0000

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1825. Min Act: -0.0000

Data Index: 761352 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1918. Min Act: -0.0000

Data Index: 301298 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1681. Min Act: -0.0000

Data Index: 517928 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1831. Min Act: -0.0000

Data Index: 388314 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1882. Min Act: -0.0000

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 978