Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 870 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1682. Min Act: -0.0002

Data Index: 41489 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1593. Min Act: -0.0002

Data Index: 977134 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1470. Min Act: -0.0002

Data Index: 708976 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1515. Min Act: -0.0002

Data Index: 227474 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1320. Min Act: -0.0002

Data Index: 262402 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1477. Min Act: -0.0002

Data Index: 927301 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1226594 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1199. Min Act: -0.0002

Data Index: 86777 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1571. Min Act: -0.0002

Data Index: 688173 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1413. Min Act: -0.0002

Data Index: 921862 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1309. Min Act: -0.0002

Data Index: 174391 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1334. Min Act: -0.0002

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1249. Min Act: -0.0002

Data Index: 9224 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1248. Min Act: -0.0002

Data Index: 759832 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1279491 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1089082 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1337654 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1004829 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1325273 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.1682. Min Range: -0.1682

Max Act: 0.1234. Min Act: -0.0002

Data Index: 699973 (C4 (Web Text))

Max Activating Token Index: 134