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

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

Neuron 4519 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4892. Min Range: -2.4892

Max Act: 2.4042. Min Act: -0.0000

Data Index: 574097 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.4892. Min Range: -2.4892

Max Act: 2.4892. Min Act: -0.0000

Data Index: 803704 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 2.4892. Min Range: -2.4892

Max Act: 2.1684. Min Act: -0.0000

Data Index: 185024 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1018211 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.6603. Min Act: -0.0000

Data Index: 347810 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.9550. Min Act: -0.0000

Data Index: 326350 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.8179. Min Act: -0.0000

Data Index: 839542 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.9501. Min Act: -0.0000

Data Index: 959799 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.7334. Min Act: -0.0000

Data Index: 1136299 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.7128. Min Act: -0.0000

Data Index: 563414 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.7540. Min Act: -0.0000

Data Index: 723942 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1351785 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1352020 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.8206. Min Act: -0.0000

Data Index: 301962 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1144083 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.7140. Min Act: -0.0000

Data Index: 576194 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.9190. Min Act: -0.0000

Data Index: 885198 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.6026. Min Act: -0.0000

Data Index: 387546 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.6873. Min Act: -0.0000

Data Index: 761187 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 2.4892. Min Range: -2.4892

Max Act: 1.5846. Min Act: -0.0000

Data Index: 862131 (C4 (Web Text))

Max Activating Token Index: 701