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

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

Neuron 4246 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.4426. Min Act: -0.0000

Data Index: 76916 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.1840. Min Act: -0.0000

Data Index: 234729 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.2450. Min Act: -0.0000

Data Index: 766427 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.3372. Min Act: -0.0000

Data Index: 454439 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.1741. Min Act: -0.0000

Data Index: 629314 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.0766. Min Act: -0.0000

Data Index: 580479 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.0253. Min Act: -0.0000

Data Index: 299649 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9881. Min Act: -0.0000

Data Index: 877234 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 2.4426. Min Range: -2.4426

Max Act: 2.0715. Min Act: -0.0000

Data Index: 1020804 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9087. Min Act: -0.0000

Data Index: 162957 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9166. Min Act: -0.0000

Data Index: 909371 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.7874. Min Act: -0.0000

Data Index: 885221 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9392. Min Act: -0.0000

Data Index: 481853 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.8339. Min Act: -0.0000

Data Index: 545729 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.9370. Min Act: -0.0000

Data Index: 1309613 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.7974. Min Act: -0.0000

Data Index: 1323228 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.7564. Min Act: -0.0000

Data Index: 156960 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.6645. Min Act: -0.0000

Data Index: 919488 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.6727. Min Act: -0.0000

Data Index: 495121 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 2.4426. Min Range: -2.4426

Max Act: 1.7641. Min Act: -0.0000

Data Index: 53344 (C4 (Web Text))

Max Activating Token Index: 279