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

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

Neuron 3844 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.7380. Min Act: -0.0001

Data Index: 590595 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5184. Min Act: -0.0001

Data Index: 956978 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5999. Min Act: -0.0001

Data Index: 1081436 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5614. Min Act: -0.0001

Data Index: 180781 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5782. Min Act: -0.0001

Data Index: 522312 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5649. Min Act: -0.0001

Data Index: 88885 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.5822. Min Act: -0.0001

Data Index: 784785 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4943. Min Act: -0.0001

Data Index: 1337795 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1039749 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4626. Min Act: -0.0001

Data Index: 655679 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4750. Min Act: -0.0001

Data Index: 816786 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1137443 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4553. Min Act: -0.0001

Data Index: 567217 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4481. Min Act: -0.0001

Data Index: 142093 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4394. Min Act: -0.0001

Data Index: 637783 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4195. Min Act: -0.0001

Data Index: 514789 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.3965. Min Act: -0.0001

Data Index: 542660 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4332. Min Act: -0.0001

Data Index: 1166201 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1032517 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.7380. Min Range: -0.7380

Max Act: 0.4058. Min Act: -0.0001

Data Index: 950325 (C4 (Web Text))

Max Activating Token Index: 587