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

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

Neuron 3788 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4907. Min Act: -0.0000

Data Index: 162662 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1242193 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1288937 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4155. Min Act: -0.0000

Data Index: 619573 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1076696 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4513. Min Act: -0.0000

Data Index: 759071 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4592. Min Act: -0.0000

Data Index: 144917 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1140906 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4790. Min Act: -0.0000

Data Index: 560101 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4442. Min Act: -0.0000

Data Index: 166986 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4571. Min Act: -0.0000

Data Index: 46224 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4249. Min Act: -0.0000

Data Index: 579650 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4153. Min Act: -0.0000

Data Index: 815890 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1315660 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4286. Min Act: -0.0000

Data Index: 455163 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1246254 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1075807 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.3916. Min Act: -0.0000

Data Index: 746118 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.5025. Min Range: -0.5025

Max Act: 0.4364. Min Act: -0.0000

Data Index: 475451 (C4 (Web Text))

Max Activating Token Index: 589