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

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

Neuron 1128 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: 0.2333. Min Range: -0.2333

Max Act: 0.2333. Min Act: -0.0001

Data Index: 478796 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2274. Min Act: -0.0001

Data Index: 825381 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2147. Min Act: -0.0001

Data Index: 807554 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1688. Min Act: -0.0001

Data Index: 944035 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1499. Min Act: -0.0001

Data Index: 590160 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1604. Min Act: -0.0001

Data Index: 484061 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1189147 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1637. Min Act: -0.0001

Data Index: 185143 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1458. Min Act: -0.0001

Data Index: 594043 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1243986 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1440. Min Act: -0.0001

Data Index: 330449 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1255332 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1373. Min Act: -0.0001

Data Index: 252204 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1054185 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1425. Min Act: -0.0001

Data Index: 315559 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1229. Min Act: -0.0001

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1517. Min Act: -0.0001

Data Index: 73228 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1282856 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1234301 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1358. Min Act: -0.0001

Data Index: 377617 (C4 (Web Text))

Max Activating Token Index: 545