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

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

Neuron 59 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2489. Min Act: -0.0000

Data Index: 918933 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1137381 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1302808 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.2152. Min Act: -0.0000

Data Index: 752106 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1847. Min Act: -0.0000

Data Index: 990995 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1385785 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1624409 (Python Code)

Max Activating Token Index: 658

Text #7

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1510. Min Act: -0.0000

Data Index: 522747 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1601571 (Python Code)

Max Activating Token Index: 917

Text #9

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1461. Min Act: -0.0000

Data Index: 118293 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1290358 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1433. Min Act: -0.0000

Data Index: 846865 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1359437 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1425662 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1502. Min Act: -0.0000

Data Index: 600916 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1182533 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1374534 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1479. Min Act: -0.0000

Data Index: 298477 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1515183 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 0.2489. Min Range: -0.2489

Max Act: 0.1356. Min Act: -0.0000

Data Index: 87052 (C4 (Web Text))

Max Activating Token Index: 591