Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6030 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.2618. Min Act: -0.0000

Data Index: 1054862 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.2601. Min Act: -0.0000

Data Index: 1271201 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.1844. Min Act: -0.0000

Data Index: 170286 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.1781. Min Act: -0.0000

Data Index: 122940 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.1118. Min Act: -0.0000

Data Index: 296241 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.9561. Min Act: -0.0000

Data Index: 1139230 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0596. Min Act: -0.0000

Data Index: 174627 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0394. Min Act: -0.0000

Data Index: 292586 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0393. Min Act: -0.0000

Data Index: 1244955 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.9644. Min Act: -0.0000

Data Index: 240737 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.9625. Min Act: -0.0000

Data Index: 199452 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0256. Min Act: -0.0000

Data Index: 1183798 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1293867 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.9143. Min Act: -0.0000

Data Index: 530462 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0563. Min Act: -0.0000

Data Index: 80651 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.8828. Min Act: -0.0000

Data Index: 969444 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.8979. Min Act: -0.0000

Data Index: 260281 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.8586. Min Act: -0.0000

Data Index: 403692 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 3.2618. Min Range: -3.2618

Max Act: 3.0041. Min Act: -0.0000

Data Index: 1015376 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 3.2618. Min Range: -3.2618

Max Act: 2.7114. Min Act: -0.0000

Data Index: 863893 (C4 (Web Text))

Max Activating Token Index: 941