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

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

Neuron 1821 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: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0001

Data Index: 570192 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0354. Min Act: -0.0002

Data Index: 240905 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0001

Data Index: 794456 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1096607 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0352. Min Act: -0.0001

Data Index: 19963 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0338. Min Act: -0.0002

Data Index: 715997 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0338. Min Act: -0.0002

Data Index: 669879 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0339. Min Act: -0.0001

Data Index: 686900 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1246782 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0330. Min Act: -0.0002

Data Index: 979897 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1452473 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0326. Min Act: -0.0002

Data Index: 914263 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1225499 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1244214 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1501155 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0283. Min Act: -0.0001

Data Index: 337241 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0283. Min Act: -0.0001

Data Index: 588558 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0287. Min Act: -0.0001

Data Index: 587183 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0286. Min Act: -0.0002

Data Index: 199019 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1350437 (C4 (Web Text))

Max Activating Token Index: 516