Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 87 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1274714 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1075083 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0323. Min Act: -0.0006

Data Index: 390132 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0322. Min Act: -0.0006

Data Index: 754924 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0320. Min Act: -0.0006

Data Index: 8128 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0297. Min Act: -0.0006

Data Index: 639065 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0006

Data Index: 526486 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0314. Min Act: -0.0006

Data Index: 842656 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0304. Min Act: -0.0006

Data Index: 1029495 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0006

Data Index: 479233 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0310. Min Act: -0.0006

Data Index: 406403 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0310. Min Act: -0.0006

Data Index: 47920 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0306. Min Act: -0.0006

Data Index: 434041 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1002321 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1247480 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0298. Min Act: -0.0006

Data Index: 522904 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0286. Min Act: -0.0006

Data Index: 870680 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0296. Min Act: -0.0006

Data Index: 322640 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0294. Min Act: -0.0005

Data Index: 1337073 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1217280 (C4 (Web Text))

Max Activating Token Index: 393