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

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

Neuron 4610 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: 0.2556. Min Range: -0.2556

Max Act: 0.2550. Min Act: -0.0002

Data Index: 1348332 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2556. Min Act: -0.0002

Data Index: 36304 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2491. Min Act: -0.0002

Data Index: 291500 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2443. Min Act: -0.0002

Data Index: 437083 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2419. Min Act: -0.0002

Data Index: 1202661 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2416. Min Act: -0.0002

Data Index: 1076460 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2394. Min Act: -0.0002

Data Index: 860366 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2369. Min Act: -0.0002

Data Index: 369539 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2397. Min Act: -0.0002

Data Index: 1097637 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2370. Min Act: -0.0002

Data Index: 195014 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2345. Min Act: -0.0002

Data Index: 892078 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2287. Min Act: -0.0002

Data Index: 103677 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2285. Min Act: -0.0002

Data Index: 354202 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2221. Min Act: -0.0002

Data Index: 230898 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2190. Min Act: -0.0002

Data Index: 237102 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2207. Min Act: -0.0002

Data Index: 58602 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2170. Min Act: -0.0002

Data Index: 1163055 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2159. Min Act: -0.0002

Data Index: 82454 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2197. Min Act: -0.0002

Data Index: 346858 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2228. Min Act: -0.0002

Data Index: 996678 (C4 (Web Text))

Max Activating Token Index: 686