Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2222. Min Act: -0.0001

Data Index: 737701 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1673. Min Act: -0.0001

Data Index: 955120 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1630. Min Act: -0.0001

Data Index: 669851 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1342550 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1555. Min Act: -0.0001

Data Index: 893383 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1637. Min Act: -0.0001

Data Index: 94627 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1208815 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1500. Min Act: -0.0001

Data Index: 1166839 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1541. Min Act: -0.0001

Data Index: 173009 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1432. Min Act: -0.0001

Data Index: 506249 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1439. Min Act: -0.0001

Data Index: 301618 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1414. Min Act: -0.0001

Data Index: 883133 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1220795 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1453. Min Act: -0.0001

Data Index: 956812 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1402. Min Act: -0.0001

Data Index: 198405 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1219150 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1183450 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1369. Min Act: -0.0001

Data Index: 240992 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1364. Min Act: -0.0001

Data Index: 693929 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1360. Min Act: -0.0001

Data Index: 708763 (C4 (Web Text))

Max Activating Token Index: 874