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

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

Neuron 4239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1135795 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0533. Min Act: -0.0001

Data Index: 186272 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1034074 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0385. Min Act: -0.0001

Data Index: 229708 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0368. Min Act: -0.0001

Data Index: 645148 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1155716 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0375. Min Act: -0.0001

Data Index: 918490 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0394. Min Act: -0.0001

Data Index: 972879 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1469814 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0374. Min Act: -0.0001

Data Index: 38957 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1268495 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1096087 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0340. Min Act: -0.0001

Data Index: 340112 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0304. Min Act: -0.0001

Data Index: 264304 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0318. Min Act: -0.0001

Data Index: 975092 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0329. Min Act: -0.0001

Data Index: 930429 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0345. Min Act: -0.0001

Data Index: 503002 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0270. Min Act: -0.0001

Data Index: 391143 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1047659 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0297. Min Act: -0.0001

Data Index: 365339 (C4 (Web Text))

Max Activating Token Index: 261