Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.7149. Min Act: -0.0001

Data Index: 856714 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1248810 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1090869 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5570. Min Act: -0.0000

Data Index: 572458 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5340. Min Act: -0.0000

Data Index: 191635 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5606. Min Act: -0.0001

Data Index: 279241 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5855. Min Act: -0.0001

Data Index: 841401 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.4849. Min Act: -0.0001

Data Index: 904030 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.4388. Min Act: -0.0000

Data Index: 946445 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3892. Min Act: -0.0000

Data Index: 61976 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5299. Min Act: -0.0001

Data Index: 482485 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3949. Min Act: -0.0001

Data Index: 145513 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.4484. Min Act: -0.0000

Data Index: 897118 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.5604. Min Act: -0.0001

Data Index: 498093 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.4274. Min Act: -0.0000

Data Index: 126621 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3502. Min Act: -0.0001

Data Index: 316536 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.4498. Min Act: -0.0001

Data Index: 173980 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3441. Min Act: -0.0001

Data Index: 1271867 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3039. Min Act: -0.0001

Data Index: 769814 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.7149. Min Range: -1.7149

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1312981 (C4 (Web Text))

Max Activating Token Index: 534