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

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

Neuron 4561 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0003

Data Index: 405724 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0362. Min Act: -0.0003

Data Index: 575884 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1056402 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0333. Min Act: -0.0003

Data Index: 110504 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0345. Min Act: -0.0003

Data Index: 132123 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0329. Min Act: -0.0003

Data Index: 772089 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0333. Min Act: -0.0003

Data Index: 940047 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0309. Min Act: -0.0003

Data Index: 341125 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0295. Min Act: -0.0003

Data Index: 246486 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1297745 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0304. Min Act: -0.0003

Data Index: 724210 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0312. Min Act: -0.0003

Data Index: 611211 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0315. Min Act: -0.0003

Data Index: 462471 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0300. Min Act: -0.0003

Data Index: 543931 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0302. Min Act: -0.0003

Data Index: 92973 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1024151 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0300. Min Act: -0.0003

Data Index: 81367 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0293. Min Act: -0.0003

Data Index: 279076 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1224902 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1198055 (C4 (Web Text))

Max Activating Token Index: 484