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

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

Neuron 2640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0395. Min Act: -0.0002

Data Index: 691773 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0412. Min Act: -0.0002

Data Index: 514399 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1334929 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1527658 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1466394 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0327. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0329. Min Act: -0.0002

Data Index: 710332 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0321. Min Act: -0.0002

Data Index: 433052 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0338. Min Act: -0.0002

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0298. Min Act: -0.0002

Data Index: 904744 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1550152 (Python Code)

Max Activating Token Index: 850

Text #12

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0304. Min Act: -0.0002

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0310. Min Act: -0.0002

Data Index: 184067 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0297. Min Act: -0.0002

Data Index: 396527 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0314. Min Act: -0.0002

Data Index: 982001 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1068056 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1405223 (Python Code)

Max Activating Token Index: 775

Text #18

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0287. Min Act: -0.0002

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0445. Min Range: -0.0445

Max Act: 0.0293. Min Act: -0.0002

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 562