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

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

Neuron 727 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1299399 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1013490 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0459. Min Act: -0.0002

Data Index: 887225 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1027075 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0414. Min Act: -0.0001

Data Index: 512008 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0412. Min Act: -0.0002

Data Index: 944009 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0401. Min Act: -0.0002

Data Index: 812001 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0392. Min Act: -0.0002

Data Index: 332970 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0382. Min Act: -0.0002

Data Index: 746447 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0388. Min Act: -0.0002

Data Index: 559884 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0386. Min Act: -0.0002

Data Index: 313295 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1044279 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1089470 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0384. Min Act: -0.0002

Data Index: 304840 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0376. Min Act: -0.0002

Data Index: 57841 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0378. Min Act: -0.0002

Data Index: 955355 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0378. Min Act: -0.0002

Data Index: 954118 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0368. Min Act: -0.0002

Data Index: 917569 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1212608 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.0533. Min Range: -0.0533

Max Act: 0.0369. Min Act: -0.0002

Data Index: 130862 (C4 (Web Text))

Max Activating Token Index: 74