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

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

Neuron 4337 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1342867 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1722. Min Act: -0.0001

Data Index: 107020 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1608. Min Act: -0.0001

Data Index: 267628 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1112124 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1659. Min Act: -0.0001

Data Index: 627372 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1033272 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1640. Min Act: -0.0000

Data Index: 264327 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1620. Min Act: -0.0001

Data Index: 401861 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1705. Min Act: -0.0001

Data Index: 342961 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1636. Min Act: -0.0001

Data Index: 936808 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1168867 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1588. Min Act: -0.0000

Data Index: 560207 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1529. Min Act: -0.0001

Data Index: 789145 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1481. Min Act: -0.0001

Data Index: 649639 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1521. Min Act: -0.0001

Data Index: 192229 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1549. Min Act: -0.0001

Data Index: 204118 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1325. Min Act: -0.0001

Data Index: 74949 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1484. Min Act: -0.0001

Data Index: 477167 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1006819 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.1983. Min Range: -0.1983

Max Act: 0.1480. Min Act: -0.0000

Data Index: 644312 (C4 (Web Text))

Max Activating Token Index: 340