Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 306 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.2228. Min Range: -5.2228

Max Act: 5.2228. Min Act: -0.0000

Data Index: 134180 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 5.2228. Min Range: -5.2228

Max Act: 5.1452. Min Act: -0.0000

Data Index: 1121178 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.6474. Min Act: -0.0000

Data Index: 1241453 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.3796. Min Act: -0.0000

Data Index: 103381 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.7587. Min Act: -0.0000

Data Index: 1531410 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.3614. Min Act: -0.0000

Data Index: 1145256 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.1717. Min Act: -0.0000

Data Index: 778675 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.0643. Min Act: -0.0000

Data Index: 333813 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.1975. Min Act: -0.0000

Data Index: 615399 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.0451. Min Act: -0.0000

Data Index: 149286 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.0680. Min Act: -0.0000

Data Index: 789748 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.1384. Min Act: -0.0000

Data Index: 1257041 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.3022. Min Act: -0.0000

Data Index: 350835 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.2652. Min Act: -0.0000

Data Index: 1406927 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 5.2228. Min Range: -5.2228

Max Act: 3.8681. Min Act: -0.0000

Data Index: 1794190 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 5.2228. Min Range: -5.2228

Max Act: 3.8261. Min Act: -0.0000

Data Index: 1783876 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 5.2228. Min Range: -5.2228

Max Act: 4.2739. Min Act: -0.0000

Data Index: 1292160 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 5.2228. Min Range: -5.2228

Max Act: 3.7326. Min Act: -0.0000

Data Index: 974732 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 5.2228. Min Range: -5.2228

Max Act: 3.8466. Min Act: -0.0000

Data Index: 300353 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 5.2228. Min Range: -5.2228

Max Act: 3.6814. Min Act: -0.0000

Data Index: 953583 (The Pile)

Max Activating Token Index: 751