Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 414 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1513919 (Python Code)

Max Activating Token Index: 975

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0401. Min Act: -0.0000

Data Index: 382550 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1252317 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1430914 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1486298 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1263583 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0312. Min Act: -0.0000

Data Index: 702691 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0328. Min Act: -0.0000

Data Index: 563942 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0280. Min Act: -0.0000

Data Index: 859251 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1556924 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1499644 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0296. Min Act: -0.0000

Data Index: 523625 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1547230 (Python Code)

Max Activating Token Index: 541

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1363045 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1525897 (Python Code)

Max Activating Token Index: 645

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0293. Min Act: -0.0000

Data Index: 981943 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0269. Min Act: -0.0000

Data Index: 1648641 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0289. Min Act: -0.0000

Data Index: 867258 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0300. Min Act: -0.0000

Data Index: 613684 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0272. Min Act: -0.0000

Data Index: 677325 (C4 (Web Text))

Max Activating Token Index: 244