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

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

Neuron 1074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1194. Min Range: -1.1194

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1030884 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9654. Min Act: -0.0000

Data Index: 894693 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9690. Min Act: -0.0000

Data Index: 332566 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9370. Min Act: -0.0000

Data Index: 83205 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9283. Min Act: -0.0000

Data Index: 51603 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1276602 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8856. Min Act: -0.0000

Data Index: 254569 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.9330. Min Act: -0.0000

Data Index: 205112 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7973. Min Act: -0.0000

Data Index: 690992 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8060. Min Act: -0.0000

Data Index: 583283 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.8045. Min Act: -0.0000

Data Index: 132886 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7933. Min Act: -0.0000

Data Index: 981819 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7375. Min Act: -0.0000

Data Index: 190644 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7826. Min Act: -0.0000

Data Index: 594933 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1334813 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7648. Min Act: -0.0000

Data Index: 383092 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7618. Min Act: -0.0000

Data Index: 480764 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7290. Min Act: -0.0000

Data Index: 622066 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7527. Min Act: -0.0000

Data Index: 641794 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.1194. Min Range: -1.1194

Max Act: 0.7169. Min Act: -0.0000

Data Index: 826130 (C4 (Web Text))

Max Activating Token Index: 803