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

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

Neuron 270 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: 0.0428. Min Range: -0.0428

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1067147 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0344. Min Act: -0.0003

Data Index: 655062 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1325741 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0312. Min Act: -0.0003

Data Index: 425824 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0353. Min Act: -0.0003

Data Index: 717063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0354. Min Act: -0.0003

Data Index: 658263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0325. Min Act: -0.0003

Data Index: 709269 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0332. Min Act: -0.0003

Data Index: 614316 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0339. Min Act: -0.0003

Data Index: 555993 (C4 (Web Text))

Max Activating Token Index: 325

Text #9

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0322. Min Act: -0.0003

Data Index: 851422 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0305. Min Act: -0.0003

Data Index: 391055 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0319. Min Act: -0.0003

Data Index: 202540 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0326. Min Act: -0.0003

Data Index: 762453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0290. Min Act: -0.0003

Data Index: 406280 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0302. Min Act: -0.0003

Data Index: 889830 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1315953 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0296. Min Act: -0.0003

Data Index: 719313 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0304. Min Act: -0.0003

Data Index: 758638 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0298. Min Act: -0.0003

Data Index: 753949 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.0428. Min Range: -0.0428

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1091547 (C4 (Web Text))

Max Activating Token Index: 87