Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1184 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0003

Data Index: 95060 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0667. Min Act: -0.0003

Data Index: 933097 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0653. Min Act: -0.0003

Data Index: 429363 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0613. Min Act: -0.0004

Data Index: 1255384 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0591. Min Act: -0.0004

Data Index: 752498 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0592. Min Act: -0.0003

Data Index: 88115 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0589. Min Act: -0.0004

Data Index: 67512 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0577. Min Act: -0.0003

Data Index: 498911 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1102048 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0588. Min Act: -0.0003

Data Index: 453425 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0581. Min Act: -0.0004

Data Index: 692658 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1105925 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0576. Min Act: -0.0003

Data Index: 28812 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1125517 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0585. Min Act: -0.0004

Data Index: 1251261 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0582. Min Act: -0.0003

Data Index: 870886 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0004

Data Index: 45754 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0583. Min Act: -0.0003

Data Index: 174 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0555. Min Act: -0.0003

Data Index: 690201 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0567. Min Act: -0.0004

Data Index: 1265877 (C4 (Web Text))

Max Activating Token Index: 276