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

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

Neuron 2780 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1951. Min Act: -0.0000

Data Index: 774700 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1780. Min Act: -0.0000

Data Index: 216308 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1776. Min Act: -0.0000

Data Index: 664501 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1754. Min Act: -0.0000

Data Index: 99986 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1219479 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1479. Min Act: -0.0000

Data Index: 630829 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1505. Min Act: -0.0000

Data Index: 140015 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1498. Min Act: -0.0000

Data Index: 418126 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1539. Min Act: -0.0000

Data Index: 194088 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1421. Min Act: -0.0000

Data Index: 699612 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1414. Min Act: -0.0000

Data Index: 590821 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1458. Min Act: -0.0000

Data Index: 994440 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1301. Min Act: -0.0000

Data Index: 1242318 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1298. Min Act: -0.0000

Data Index: 538979 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1281. Min Act: -0.0000

Data Index: 936214 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1278883 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1327080 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1080. Min Act: -0.0000

Data Index: 501911 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1201. Min Act: -0.0000

Data Index: 83354 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.1951. Min Range: -0.1951

Max Act: 0.1198. Min Act: -0.0000

Data Index: 522169 (C4 (Web Text))

Max Activating Token Index: 488