Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 913 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7985. Min Act: -0.0000

Data Index: 352428 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7699. Min Act: -0.0000

Data Index: 658122 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7626. Min Act: -0.0000

Data Index: 881518 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7391. Min Act: -0.0000

Data Index: 191087 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7085. Min Act: -0.0000

Data Index: 61417 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1269296 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1311108 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6457. Min Act: -0.0000

Data Index: 265447 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6690. Min Act: -0.0000

Data Index: 899292 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6862. Min Act: -0.0000

Data Index: 229891 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.7222. Min Act: -0.0000

Data Index: 444971 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6839. Min Act: -0.0000

Data Index: 484762 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6690. Min Act: -0.0000

Data Index: 747533 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6498. Min Act: -0.0000

Data Index: 926824 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6698. Min Act: -0.0000

Data Index: 264991 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1240260 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6607. Min Act: -0.0000

Data Index: 848993 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6195. Min Act: -0.0000

Data Index: 43234 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.6415. Min Act: -0.0000

Data Index: 780510 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.7985. Min Range: -0.7985

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1246840 (C4 (Web Text))

Max Activating Token Index: 293