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

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

Neuron 1434 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: 2.9443. Min Range: -2.9443

Max Act: 2.9443. Min Act: -0.0000

Data Index: 426941 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.5459. Min Act: -0.0000

Data Index: 466729 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.4388. Min Act: -0.0000

Data Index: 966699 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.4472. Min Act: -0.0000

Data Index: 1126971 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.4330. Min Act: -0.0000

Data Index: 895822 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3715. Min Act: -0.0000

Data Index: 977024 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2528. Min Act: -0.0000

Data Index: 888092 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3403. Min Act: -0.0000

Data Index: 549278 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3524. Min Act: -0.0000

Data Index: 871027 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1047255 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3242. Min Act: -0.0000

Data Index: 619206 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3859. Min Act: -0.0000

Data Index: 1328203 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2693. Min Act: -0.0000

Data Index: 906975 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.1567. Min Act: -0.0000

Data Index: 841806 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2742. Min Act: -0.0000

Data Index: 487469 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2623. Min Act: -0.0000

Data Index: 844734 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.1567. Min Act: -0.0000

Data Index: 500199 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2437. Min Act: -0.0000

Data Index: 978534 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.3369. Min Act: -0.0000

Data Index: 503491 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 2.9443. Min Range: -2.9443

Max Act: 2.2656. Min Act: -0.0000

Data Index: 284797 (C4 (Web Text))

Max Activating Token Index: 543