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

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

Neuron 3021 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.7645. Min Act: -0.0000

Data Index: 1434511 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.4498. Min Act: -0.0001

Data Index: 927916 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.4455. Min Act: -0.0001

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.4591. Min Act: -0.0001

Data Index: 795531 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.3301. Min Act: -0.0000

Data Index: 989584 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.3263. Min Act: -0.0000

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1029407 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2207. Min Act: -0.0001

Data Index: 701306 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2943. Min Act: -0.0001

Data Index: 1184475 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2773. Min Act: -0.0001

Data Index: 1187293 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.1664. Min Act: -0.0001

Data Index: 910591 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2067. Min Act: -0.0001

Data Index: 709505 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1440216 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1192155 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2061. Min Act: -0.0001

Data Index: 1164884 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1329878 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2295. Min Act: -0.0001

Data Index: 340232 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1047391 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2001. Min Act: -0.0000

Data Index: 771571 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.7645. Min Range: -1.7645

Max Act: 1.2090. Min Act: -0.0001

Data Index: 238390 (C4 (Web Text))

Max Activating Token Index: 536