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

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

Neuron 276 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.8367. Min Act: -0.0000

Data Index: 359853 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 3.0472. Min Range: -3.0472

Max Act: 3.0472. Min Act: -0.0001

Data Index: 1011676 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.4186. Min Act: -0.0001

Data Index: 223988 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.4402. Min Act: -0.0001

Data Index: 1223039 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.5196. Min Act: -0.0001

Data Index: 851498 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.5749. Min Act: -0.0001

Data Index: 655629 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.2795. Min Act: -0.0000

Data Index: 34281 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.2587. Min Act: -0.0001

Data Index: 870588 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.2655. Min Act: -0.0001

Data Index: 820729 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.3677. Min Act: -0.0001

Data Index: 455141 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.2821. Min Act: -0.0001

Data Index: 428429 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.1453. Min Act: -0.0001

Data Index: 85844 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.3814. Min Act: -0.0001

Data Index: 403684 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 3.0472. Min Range: -3.0472

Max Act: 1.9556. Min Act: -0.0001

Data Index: 605861 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.0628. Min Act: -0.0001

Data Index: 1218272 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.4163. Min Act: -0.0000

Data Index: 316500 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.1671. Min Act: -0.0001

Data Index: 523874 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.1294. Min Act: -0.0001

Data Index: 326761 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.2312. Min Act: -0.0001

Data Index: 1013854 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 3.0472. Min Range: -3.0472

Max Act: 2.3179. Min Act: -0.0001

Data Index: 659774 (C4 (Web Text))

Max Activating Token Index: 729