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

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

Neuron 976 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1137753 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1106092 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.3152. Min Act: -0.0000

Data Index: 519204 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1239261 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1224064 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2779. Min Act: -0.0001

Data Index: 910928 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2906. Min Act: -0.0000

Data Index: 9552 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2705. Min Act: -0.0000

Data Index: 828389 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2871. Min Act: -0.0000

Data Index: 979829 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2740. Min Act: -0.0001

Data Index: 336016 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2656. Min Act: -0.0000

Data Index: 293854 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2422. Min Act: -0.0000

Data Index: 909233 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1182742 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2568. Min Act: -0.0000

Data Index: 521021 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2386. Min Act: -0.0001

Data Index: 146621 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2375. Min Act: -0.0001

Data Index: 213924 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2512. Min Act: -0.0000

Data Index: 621108 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2444. Min Act: -0.0000

Data Index: 187454 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2502. Min Act: -0.0000

Data Index: 843566 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.3355. Min Range: -0.3355

Max Act: 0.2510. Min Act: -0.0001

Data Index: 1233673 (C4 (Web Text))

Max Activating Token Index: 361