Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2091 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.9607. Min Act: -0.0001

Data Index: 568958 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.9585. Min Act: -0.0001

Data Index: 352722 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1128133 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1298802 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8838. Min Act: -0.0000

Data Index: 888388 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8380. Min Act: -0.0001

Data Index: 191553 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7879. Min Act: -0.0001

Data Index: 969967 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8275. Min Act: -0.0001

Data Index: 299688 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1161186 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8201. Min Act: -0.0000

Data Index: 891444 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7863. Min Act: -0.0000

Data Index: 787114 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8347. Min Act: -0.0001

Data Index: 466069 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8541. Min Act: -0.0001

Data Index: 1199096 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7658. Min Act: -0.0000

Data Index: 198028 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7840. Min Act: -0.0000

Data Index: 251968 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7594. Min Act: -0.0001

Data Index: 1077691 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7322. Min Act: -0.0000

Data Index: 941070 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7817. Min Act: -0.0000

Data Index: 922806 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.8300. Min Act: -0.0000

Data Index: 60463 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.9607. Min Range: -0.9607

Max Act: 0.7744. Min Act: -0.0000

Data Index: 524808 (C4 (Web Text))

Max Activating Token Index: 372