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

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

Neuron 2970 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: 0.8447. Min Range: -0.8447

Max Act: 0.8447. Min Act: -0.0002

Data Index: 1039123 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.7326. Min Act: -0.0002

Data Index: 1024440 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6994. Min Act: -0.0002

Data Index: 1129035 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6765. Min Act: -0.0002

Data Index: 463781 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6800. Min Act: -0.0002

Data Index: 645653 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6599. Min Act: -0.0002

Data Index: 6134 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6521. Min Act: -0.0002

Data Index: 382259 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6611. Min Act: -0.0002

Data Index: 895279 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6415. Min Act: -0.0002

Data Index: 1245175 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6503. Min Act: -0.0002

Data Index: 648339 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6358. Min Act: -0.0002

Data Index: 1538665 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6317. Min Act: -0.0002

Data Index: 1263517 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6348. Min Act: -0.0002

Data Index: 1223772 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6309. Min Act: -0.0002

Data Index: 812212 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6290. Min Act: -0.0002

Data Index: 1066423 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6234. Min Act: -0.0002

Data Index: 833199 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6164. Min Act: -0.0002

Data Index: 1070040 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6253. Min Act: -0.0002

Data Index: 346342 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6195. Min Act: -0.0002

Data Index: 326168 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.8447. Min Range: -0.8447

Max Act: 0.6168. Min Act: -0.0002

Data Index: 554562 (C4 (Web Text))

Max Activating Token Index: 457