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

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

Neuron 4275 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: 1.1636. Min Range: -1.1636

Max Act: 1.1636. Min Act: -0.0000

Data Index: 286532 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0087. Min Act: -0.0000

Data Index: 134136 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0770. Min Act: -0.0000

Data Index: 37536 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.1636. Min Range: -1.1636

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1223033 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9819. Min Act: -0.0000

Data Index: 950394 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1355182 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8768. Min Act: -0.0000

Data Index: 259319 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8234. Min Act: -0.0000

Data Index: 689225 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.9032. Min Act: -0.0000

Data Index: 387392 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1123551 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8360. Min Act: -0.0000

Data Index: 805988 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1186672 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8205. Min Act: -0.0000

Data Index: 396649 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8677. Min Act: -0.0000

Data Index: 929264 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8160. Min Act: -0.0000

Data Index: 350383 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8286. Min Act: -0.0000

Data Index: 977107 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.7862. Min Act: -0.0000

Data Index: 79433 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8478. Min Act: -0.0000

Data Index: 394730 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8191. Min Act: -0.0000

Data Index: 119481 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 1.1636. Min Range: -1.1636

Max Act: 0.8140. Min Act: -0.0000

Data Index: 371651 (C4 (Web Text))

Max Activating Token Index: 680