Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1155500 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1252929 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1150701 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0317. Min Act: -0.0003

Data Index: 751372 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0003

Data Index: 837034 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0309. Min Act: -0.0003

Data Index: 617776 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0298. Min Act: -0.0003

Data Index: 470089 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0003

Data Index: 334234 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0299. Min Act: -0.0003

Data Index: 500867 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0313. Min Act: -0.0003

Data Index: 259111 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0311. Min Act: -0.0003

Data Index: 713779 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1110449 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0338. Min Act: -0.0003

Data Index: 149389 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0309. Min Act: -0.0003

Data Index: 882143 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1137482 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0296. Min Act: -0.0003

Data Index: 82071 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0299. Min Act: -0.0003

Data Index: 443447 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0304. Min Act: -0.0003

Data Index: 476224 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0298. Min Act: -0.0003

Data Index: 514541 (C4 (Web Text))

Max Activating Token Index: 338