Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0001

Data Index: 473584 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1614. Min Act: -0.0002

Data Index: 753943 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1256320 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1496. Min Act: -0.0001

Data Index: 929072 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1051056 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1308087 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1431. Min Act: -0.0001

Data Index: 263452 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1429. Min Act: -0.0000

Data Index: 990405 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1159353 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1367. Min Act: -0.0002

Data Index: 102838 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1245719 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1370. Min Act: -0.0002

Data Index: 490399 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1394. Min Act: -0.0000

Data Index: 143163 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1170684 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1368. Min Act: -0.0001

Data Index: 109266 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1370. Min Act: -0.0002

Data Index: 191163 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1377. Min Act: -0.0000

Data Index: 591148 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1336. Min Act: -0.0002

Data Index: 961053 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1290. Min Act: -0.0002

Data Index: 835427 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1311. Min Act: -0.0001

Data Index: 204477 (C4 (Web Text))

Max Activating Token Index: 889