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

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

Neuron 504 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: 0.0633. Min Range: -0.0633

Max Act: 0.0630. Min Act: -0.0003

Data Index: 192313 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0003

Data Index: 491403 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0603. Min Act: -0.0002

Data Index: 718086 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0619. Min Act: -0.0003

Data Index: 646626 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1279925 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0606. Min Act: -0.0003

Data Index: 55290 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1115125 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0588. Min Act: -0.0003

Data Index: 695048 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1194712 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0577. Min Act: -0.0003

Data Index: 1010527 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1033410 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0580. Min Act: -0.0003

Data Index: 1088299 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0573. Min Act: -0.0003

Data Index: 1131098 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0585. Min Act: -0.0003

Data Index: 270004 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1118989 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1078204 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1209507 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0584. Min Act: -0.0003

Data Index: 650498 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0573. Min Act: -0.0003

Data Index: 234457 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1052989 (C4 (Web Text))

Max Activating Token Index: 241