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

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

Neuron 1899 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0001

Data Index: 665074 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5944. Min Act: -0.0001

Data Index: 237912 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5050. Min Act: -0.0001

Data Index: 305184 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5551. Min Act: -0.0001

Data Index: 1297449 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5212. Min Act: -0.0000

Data Index: 792220 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4947. Min Act: -0.0001

Data Index: 160490 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5119. Min Act: -0.0001

Data Index: 559104 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4609. Min Act: -0.0001

Data Index: 369880 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4731. Min Act: -0.0001

Data Index: 584167 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4705. Min Act: -0.0001

Data Index: 422980 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4952. Min Act: -0.0001

Data Index: 421983 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4844. Min Act: -0.0001

Data Index: 109460 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4646. Min Act: -0.0001

Data Index: 264960 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4704. Min Act: -0.0001

Data Index: 609434 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4223. Min Act: -0.0001

Data Index: 1127406 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1011816 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4507. Min Act: -0.0001

Data Index: 253357 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1045041 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4587. Min Act: -0.0001

Data Index: 163506 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4537. Min Act: -0.0001

Data Index: 65272 (C4 (Web Text))

Max Activating Token Index: 631