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

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

Neuron 4475 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.7511. Min Act: -0.0002

Data Index: 1652800 (Python Code)

Max Activating Token Index: 464

Text #1

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6929. Min Act: -0.0002

Data Index: 367238 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6761. Min Act: -0.0002

Data Index: 374343 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6740. Min Act: -0.0002

Data Index: 748739 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6639. Min Act: -0.0002

Data Index: 700451 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6553. Min Act: -0.0002

Data Index: 779604 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6608. Min Act: -0.0002

Data Index: 1320098 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6542. Min Act: -0.0002

Data Index: 67634 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6260. Min Act: -0.0002

Data Index: 1104542 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6371. Min Act: -0.0002

Data Index: 62942 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6435. Min Act: -0.0002

Data Index: 253969 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6217. Min Act: -0.0002

Data Index: 16258 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6143. Min Act: -0.0002

Data Index: 853723 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6083. Min Act: -0.0002

Data Index: 75158 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6077. Min Act: -0.0002

Data Index: 19093 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6200. Min Act: -0.0002

Data Index: 1180996 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6214. Min Act: -0.0002

Data Index: 848844 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6159. Min Act: -0.0002

Data Index: 450089 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6091. Min Act: -0.0002

Data Index: 1111912 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.7511. Min Range: -0.7511

Max Act: 0.6212. Min Act: -0.0002

Data Index: 733292 (C4 (Web Text))

Max Activating Token Index: 669