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

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

Neuron 3283 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.9149. Min Act: -0.0000

Data Index: 652839 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.8004. Min Act: -0.0000

Data Index: 870572 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6820. Min Act: -0.0000

Data Index: 330399 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6761. Min Act: -0.0000

Data Index: 432060 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7153. Min Act: -0.0000

Data Index: 458266 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6818. Min Act: -0.0000

Data Index: 80281 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6754. Min Act: -0.0000

Data Index: 290878 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1336028 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6005. Min Act: -0.0000

Data Index: 679343 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6809. Min Act: -0.0000

Data Index: 664684 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1328089 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6380. Min Act: 0.0000

Data Index: 1196749 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1359669 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1159755 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6279. Min Act: -0.0000

Data Index: 61406 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6024. Min Act: -0.0000

Data Index: 416889 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1262293 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6181. Min Act: -0.0000

Data Index: 423202 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6790. Min Act: -0.0000

Data Index: 325177 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5471. Min Act: -0.0000

Data Index: 906099 (C4 (Web Text))

Max Activating Token Index: 721