Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 651 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2317. Min Act: -0.0002

Data Index: 561053 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2140. Min Act: -0.0002

Data Index: 573155 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2063. Min Act: -0.0002

Data Index: 1218142 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2112. Min Act: -0.0002

Data Index: 116448 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2090. Min Act: -0.0002

Data Index: 983464 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1862. Min Act: -0.0002

Data Index: 100926 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2059. Min Act: -0.0002

Data Index: 348240 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1706. Min Act: -0.0002

Data Index: 758043 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1695. Min Act: -0.0002

Data Index: 1146433 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1644. Min Act: -0.0002

Data Index: 485561 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1580. Min Act: -0.0002

Data Index: 926917 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1612. Min Act: -0.0002

Data Index: 442292 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1557. Min Act: -0.0002

Data Index: 757653 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1551. Min Act: -0.0002

Data Index: 603396 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1699. Min Act: -0.0002

Data Index: 491275 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1493. Min Act: -0.0002

Data Index: 516019 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1407. Min Act: -0.0002

Data Index: 842611 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1336. Min Act: -0.0002

Data Index: 361509 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1391. Min Act: -0.0002

Data Index: 661190 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1411. Min Act: -0.0002

Data Index: 521124 (C4 (Web Text))

Max Activating Token Index: 834