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

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

Neuron 815 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: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0002

Data Index: 697469 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1324206 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0320. Min Act: -0.0002

Data Index: 590521 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0324. Min Act: -0.0002

Data Index: 111544 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0325. Min Act: -0.0002

Data Index: 205653 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0308. Min Act: -0.0002

Data Index: 751447 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1055833 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0300. Min Act: -0.0002

Data Index: 644162 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0293. Min Act: -0.0002

Data Index: 567678 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0300. Min Act: -0.0002

Data Index: 589578 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0298. Min Act: -0.0002

Data Index: 26740 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0303. Min Act: -0.0002

Data Index: 763132 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1039508 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0296. Min Act: -0.0002

Data Index: 684562 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0291. Min Act: -0.0002

Data Index: 336360 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0295. Min Act: -0.0002

Data Index: 600557 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0304. Min Act: -0.0002

Data Index: 548120 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0281. Min Act: -0.0002

Data Index: 460575 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1228078 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1299849 (C4 (Web Text))

Max Activating Token Index: 784