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

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

Neuron 525 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1776. Min Act: -0.0001

Data Index: 213618 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1229156 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1673. Min Act: -0.0001

Data Index: 196614 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1604. Min Act: -0.0001

Data Index: 687639 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1544. Min Act: -0.0001

Data Index: 350159 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1403. Min Act: -0.0001

Data Index: 405457 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1465. Min Act: -0.0001

Data Index: 389661 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1217834 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1313. Min Act: -0.0001

Data Index: 412126 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1094922 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1004015 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1174. Min Act: -0.0001

Data Index: 174390 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1331. Min Act: -0.0001

Data Index: 305157 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1375. Min Act: -0.0001

Data Index: 862733 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1321158 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1316. Min Act: -0.0001

Data Index: 777897 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1342. Min Act: -0.0001

Data Index: 966599 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1138443 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1176747 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1214. Min Act: -0.0001

Data Index: 514410 (C4 (Web Text))

Max Activating Token Index: 862