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

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

Neuron 70 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0001

Data Index: 391895 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1126852 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0420. Min Act: -0.0001

Data Index: 679417 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1204041 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0390. Min Act: -0.0001

Data Index: 608939 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0393. Min Act: -0.0001

Data Index: 50556 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0351. Min Act: -0.0001

Data Index: 883428 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0397. Min Act: -0.0001

Data Index: 718901 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1110205 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0366. Min Act: -0.0001

Data Index: 541662 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0384. Min Act: -0.0001

Data Index: 236904 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0338. Min Act: -0.0001

Data Index: 165538 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0337. Min Act: -0.0001

Data Index: 778434 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0344. Min Act: -0.0001

Data Index: 460046 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0391. Min Act: -0.0001

Data Index: 903013 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0346. Min Act: -0.0001

Data Index: 126390 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0359. Min Act: -0.0001

Data Index: 492283 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0340. Min Act: -0.0001

Data Index: 51183 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0343. Min Act: -0.0001

Data Index: 387422 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0350. Min Act: -0.0001

Data Index: 874562 (C4 (Web Text))

Max Activating Token Index: 827