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

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

Neuron 1956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0636. Min Act: -0.0006

Data Index: 214360 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0006

Data Index: 1147322 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0577. Min Act: -0.0006

Data Index: 23639 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0588. Min Act: -0.0006

Data Index: 1229367 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0569. Min Act: -0.0006

Data Index: 514086 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1203664 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0551. Min Act: -0.0006

Data Index: 856140 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0604. Min Act: -0.0006

Data Index: 332828 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0579. Min Act: -0.0006

Data Index: 1039288 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0567. Min Act: -0.0006

Data Index: 2823 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0523. Min Act: -0.0006

Data Index: 331719 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0589. Min Act: -0.0006

Data Index: 959472 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0576. Min Act: -0.0006

Data Index: 122902 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0579. Min Act: -0.0006

Data Index: 198377 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0598. Min Act: -0.0006

Data Index: 48990 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0526. Min Act: -0.0006

Data Index: 636712 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0552. Min Act: -0.0006

Data Index: 775637 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0584. Min Act: -0.0006

Data Index: 638825 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1056266 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0576. Min Act: -0.0006

Data Index: 653655 (C4 (Web Text))

Max Activating Token Index: 264