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

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

Neuron 583 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: 0.1700. Min Range: -0.1700

Max Act: 0.1700. Min Act: -0.0002

Data Index: 1239801 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1689. Min Act: -0.0002

Data Index: 109598 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1635. Min Act: -0.0002

Data Index: 224610 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1552. Min Act: -0.0002

Data Index: 532135 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1496. Min Act: -0.0002

Data Index: 204937 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1473. Min Act: -0.0002

Data Index: 788572 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1300. Min Act: 0.0000

Data Index: 1111282 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1208675 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1418. Min Act: -0.0001

Data Index: 103143 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1386. Min Act: -0.0001

Data Index: 468232 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1417. Min Act: -0.0002

Data Index: 322825 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1071976 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1357. Min Act: -0.0001

Data Index: 510289 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1354470 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1345. Min Act: -0.0002

Data Index: 113746 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1341. Min Act: -0.0002

Data Index: 180875 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1216963 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1304. Min Act: -0.0001

Data Index: 633864 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1150910 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.1700. Min Range: -0.1700

Max Act: 0.1310. Min Act: -0.0002

Data Index: 870061 (C4 (Web Text))

Max Activating Token Index: 727