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

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

Neuron 363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0383. Min Range: -5.0383

Max Act: 5.0383. Min Act: 0.0001

Data Index: 1304778 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.7768. Min Act: 0.0000

Data Index: 422707 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.6643. Min Act: 0.0000

Data Index: 380125 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.8420. Min Act: -0.0000

Data Index: 632208 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.5820. Min Act: 0.0000

Data Index: 516911 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.3547. Min Act: -0.0000

Data Index: 484605 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.4740. Min Act: 0.0000

Data Index: 151469 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.3540. Min Act: 0.0000

Data Index: 1116698 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.1704. Min Act: 0.0000

Data Index: 555225 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.1352. Min Act: 0.0000

Data Index: 613973 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.3043. Min Act: -0.0000

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.4447. Min Act: 0.0000

Data Index: 1354208 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.1523. Min Act: 0.0000

Data Index: 961805 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.1497. Min Act: -0.0000

Data Index: 452050 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 5.0383. Min Range: -5.0383

Max Act: 3.9598. Min Act: 0.0000

Data Index: 241723 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.2372. Min Act: 0.0000

Data Index: 301910 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 5.0383. Min Range: -5.0383

Max Act: 3.8629. Min Act: -0.0000

Data Index: 1204814 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 5.0383. Min Range: -5.0383

Max Act: 3.8732. Min Act: 0.0000

Data Index: 347062 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 5.0383. Min Range: -5.0383

Max Act: 3.8247. Min Act: 0.0000

Data Index: 1279942 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 5.0383. Min Range: -5.0383

Max Act: 4.0131. Min Act: 0.0000

Data Index: 23412 (C4 (Web Text))

Max Activating Token Index: 833