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

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

Neuron 3955 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: 0.0542. Min Range: -0.0542

Max Act: 0.0542. Min Act: -0.0002

Data Index: 598753 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0396. Min Act: -0.0002

Data Index: 813726 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0401. Min Act: -0.0002

Data Index: 27689 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1462344 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1483253 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1268181 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1469713 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0321. Min Act: -0.0002

Data Index: 309161 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1500156 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1388611 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1520238 (Python Code)

Max Activating Token Index: 929

Text #11

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0316. Min Act: -0.0002

Data Index: 943310 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1616098 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0324. Min Act: -0.0002

Data Index: 25210 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1389632 (Python Code)

Max Activating Token Index: 898

Text #15

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1530079 (Python Code)

Max Activating Token Index: 624

Text #16

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1410427 (Python Code)

Max Activating Token Index: 848

Text #17

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1527922 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1406312 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.0542. Min Range: -0.0542

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1410902 (Python Code)

Max Activating Token Index: 855