Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1609 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0339. Min Range: -3.0339

Max Act: 3.0339. Min Act: -0.0000

Data Index: 34465 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.8196. Min Act: -0.0000

Data Index: 567711 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.6155. Min Act: -0.0000

Data Index: 512899 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.7589. Min Act: -0.0000

Data Index: 1329820 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.3087. Min Act: -0.0000

Data Index: 1205158 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 3.0339. Min Range: -3.0339

Max Act: 2.1967. Min Act: -0.0000

Data Index: 474594 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.8757. Min Act: -0.0000

Data Index: 977963 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.8418. Min Act: 0.0000

Data Index: 1254646 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.6620. Min Act: -0.0000

Data Index: 40982 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.6516. Min Act: -0.0000

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3877. Min Act: -0.0000

Data Index: 862835 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1392276 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.4274. Min Act: -0.0000

Data Index: 419515 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.4856. Min Act: -0.0000

Data Index: 1514184 (Python Code)

Max Activating Token Index: 511

Text #14

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1063088 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1583579 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3380. Min Act: -0.0000

Data Index: 387262 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1457363 (Python Code)

Max Activating Token Index: 312

Text #18

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.3181. Min Act: -0.0000

Data Index: 68626 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.0339. Min Range: -3.0339

Max Act: 1.2986. Min Act: -0.0000

Data Index: 1468438 (Python Code)

Max Activating Token Index: 768