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

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

Neuron 3426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1718. Min Act: -0.0001

Data Index: 197200 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1763. Min Act: -0.0001

Data Index: 276324 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1663. Min Act: -0.0001

Data Index: 779674 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1340576 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1472. Min Act: -0.0001

Data Index: 724704 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1663. Min Act: -0.0001

Data Index: 334321 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1032222 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1369. Min Act: -0.0001

Data Index: 616093 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1598. Min Act: -0.0001

Data Index: 13580 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1160648 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1413. Min Act: -0.0001

Data Index: 544852 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1165868 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1086183 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1384. Min Act: -0.0001

Data Index: 565338 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1240. Min Act: -0.0001

Data Index: 882216 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1163754 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1287. Min Act: -0.0001

Data Index: 341937 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1229235 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1214. Min Act: -0.0001

Data Index: 190936 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.1763. Min Range: -0.1763

Max Act: 0.1334. Min Act: -0.0001

Data Index: 898115 (C4 (Web Text))

Max Activating Token Index: 111