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

Dataset: The Pile

Neuron 2391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2334. Min Range: -4.2334

Max Act: 4.2334. Min Act: -0.0000

Data Index: 1502839 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 4.2334. Min Range: -4.2334

Max Act: 4.1594. Min Act: -0.0000

Data Index: 972352 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.9599. Min Act: -0.0000

Data Index: 1887318 (The Pile)

Max Activating Token Index: 199

Text #3

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.5147. Min Act: -0.0000

Data Index: 220324 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.9222. Min Act: -0.0000

Data Index: 1475484 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.5225. Min Act: -0.0000

Data Index: 1384400 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.4045. Min Act: -0.0000

Data Index: 1175012 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.4006. Min Act: -0.0000

Data Index: 956115 (The Pile)

Max Activating Token Index: 511

Text #8

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.1604. Min Act: -0.0000

Data Index: 573383 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.0128. Min Act: -0.0000

Data Index: 1914541 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.2506. Min Act: -0.0000

Data Index: 74032 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.2362. Min Act: -0.0000

Data Index: 588905 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.4438. Min Act: -0.0000

Data Index: 790891 (The Pile)

Max Activating Token Index: 856

Text #13

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.1210. Min Act: -0.0000

Data Index: 1835826 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.9296. Min Act: -0.0000

Data Index: 726018 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.7522. Min Act: -0.0000

Data Index: 1663910 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 4.2334. Min Range: -4.2334

Max Act: 3.0481. Min Act: -0.0000

Data Index: 850768 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.8371. Min Act: -0.0000

Data Index: 1520485 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.7927. Min Act: -0.0000

Data Index: 993236 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 4.2334. Min Range: -4.2334

Max Act: 2.7481. Min Act: -0.0000

Data Index: 1981884 (The Pile)

Max Activating Token Index: 710