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

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

Neuron 2564 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1475129 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1183145 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1691. Min Act: -0.0001

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1458669 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1594. Min Act: -0.0001

Data Index: 499104 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1426. Min Act: -0.0001

Data Index: 835723 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1123465 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1456. Min Act: -0.0001

Data Index: 33132 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1239767 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1540. Min Act: -0.0001

Data Index: 835285 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1375. Min Act: -0.0001

Data Index: 384007 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1371. Min Act: -0.0001

Data Index: 848195 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1229384 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1356. Min Act: -0.0001

Data Index: 928999 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1474348 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1279282 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1554282 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1394. Min Act: -0.0001

Data Index: 75930 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1247. Min Act: -0.0001

Data Index: 974710 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.1840. Min Range: -0.1840

Max Act: 0.1244. Min Act: -0.0001

Data Index: 437118 (C4 (Web Text))

Max Activating Token Index: 364