Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2598 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3275. Min Act: -0.0001

Data Index: 945278 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2784. Min Act: -0.0000

Data Index: 750533 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2843. Min Act: -0.0001

Data Index: 283061 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2695. Min Act: -0.0001

Data Index: 1254892 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2594. Min Act: -0.0000

Data Index: 691764 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2734. Min Act: -0.0000

Data Index: 383535 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1143889 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2693. Min Act: -0.0000

Data Index: 1061659 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2576. Min Act: -0.0001

Data Index: 33722 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2584. Min Act: -0.0000

Data Index: 295236 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2615. Min Act: -0.0001

Data Index: 530783 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2485. Min Act: -0.0000

Data Index: 590412 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1210376 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1205166 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2377. Min Act: -0.0000

Data Index: 500850 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2427. Min Act: -0.0000

Data Index: 667716 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2327. Min Act: -0.0000

Data Index: 386894 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2486. Min Act: -0.0001

Data Index: 764522 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2391. Min Act: -0.0001

Data Index: 353007 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1312595 (C4 (Web Text))

Max Activating Token Index: 316