Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3394 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9312. Min Act: -0.0000

Data Index: 916625 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9501. Min Act: -0.0000

Data Index: 338533 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1280269 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9221. Min Act: -0.0000

Data Index: 250236 (The Pile)

Max Activating Token Index: 915

Text #4

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8525. Min Act: -0.0000

Data Index: 124692 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8665. Min Act: -0.0000

Data Index: 29386 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1142889 (The Pile)

Max Activating Token Index: 650

Text #7

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8524. Min Act: -0.0000

Data Index: 707652 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1838904 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8692. Min Act: -0.0000

Data Index: 905924 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1062225 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8503. Min Act: -0.0000

Data Index: 98269 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8740. Min Act: -0.0000

Data Index: 932180 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1789878 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8238. Min Act: -0.0000

Data Index: 148439 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8316. Min Act: -0.0000

Data Index: 134419 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8446. Min Act: -0.0000

Data Index: 19293 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1490531 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8747. Min Act: -0.0000

Data Index: 883464 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.9602. Min Range: -0.9602

Max Act: 0.8465. Min Act: -0.0000

Data Index: 288572 (The Pile)

Max Activating Token Index: 778