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

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

Neuron 1696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5537. Min Range: -4.5537

Max Act: 4.5537. Min Act: -0.0000

Data Index: 906809 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.8222. Min Act: -0.0000

Data Index: 844970 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.9525. Min Act: -0.0000

Data Index: 720421 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5462. Min Act: -0.0000

Data Index: 504348 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.5478. Min Act: -0.0000

Data Index: 1125688 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.4746. Min Act: -0.0000

Data Index: 392998 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.2453. Min Act: -0.0000

Data Index: 357010 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.1962. Min Act: -0.0000

Data Index: 917255 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.1475. Min Act: -0.0000

Data Index: 506488 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.0417. Min Act: -0.0000

Data Index: 1214058 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.8460. Min Act: -0.0000

Data Index: 214566 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.9460. Min Act: -0.0000

Data Index: 265830 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.9244. Min Act: -0.0000

Data Index: 736260 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.0382. Min Act: -0.0000

Data Index: 1023612 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.1766. Min Act: -0.0000

Data Index: 582488 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 4.5537. Min Range: -4.5537

Max Act: 3.1321. Min Act: -0.0000

Data Index: 879019 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.5801. Min Act: -0.0000

Data Index: 158348 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.7195. Min Act: -0.0000

Data Index: 597887 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.9663. Min Act: -0.0000

Data Index: 1208471 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 4.5537. Min Range: -4.5537

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1317230 (C4 (Web Text))

Max Activating Token Index: 56