Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 443 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1674. Min Act: -0.0003

Data Index: 568503 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1756. Min Act: -0.0003

Data Index: 136738 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1543. Min Act: -0.0003

Data Index: 747649 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1590. Min Act: -0.0003

Data Index: 150080 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1579. Min Act: -0.0003

Data Index: 811417 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1447. Min Act: -0.0003

Data Index: 1094830 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1444. Min Act: -0.0003

Data Index: 26049 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1408. Min Act: -0.0003

Data Index: 1090904 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1411. Min Act: -0.0003

Data Index: 1248297 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1365. Min Act: -0.0003

Data Index: 159359 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1278. Min Act: -0.0003

Data Index: 1054852 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1368. Min Act: -0.0003

Data Index: 982757 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1352. Min Act: -0.0003

Data Index: 857410 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1259. Min Act: -0.0003

Data Index: 1344581 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1342. Min Act: -0.0003

Data Index: 500032 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1334. Min Act: -0.0003

Data Index: 11053 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1288. Min Act: -0.0003

Data Index: 743514 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1285. Min Act: -0.0003

Data Index: 570639 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1285. Min Act: -0.0003

Data Index: 138104 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1194. Min Act: -0.0003

Data Index: 673603 (C4 (Web Text))

Max Activating Token Index: 837