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

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

Neuron 4138 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4952. Min Act: -0.0000

Data Index: 486461 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1245625 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1030376 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3886. Min Act: -0.0000

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3870. Min Act: -0.0000

Data Index: 166762 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3919. Min Act: -0.0000

Data Index: 225783 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.4153. Min Act: -0.0000

Data Index: 225818 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3741. Min Act: -0.0000

Data Index: 531300 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3607. Min Act: -0.0000

Data Index: 325903 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3443. Min Act: -0.0000

Data Index: 843869 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1193505 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3970. Min Act: -0.0000

Data Index: 10150 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3523. Min Act: -0.0000

Data Index: 204825 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3961. Min Act: -0.0000

Data Index: 212060 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3455. Min Act: -0.0000

Data Index: 729589 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3500. Min Act: -0.0000

Data Index: 631813 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3178. Min Act: -0.0000

Data Index: 38748 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3587. Min Act: -0.0000

Data Index: 527360 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3459. Min Act: -0.0000

Data Index: 784049 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.4952. Min Range: -0.4952

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1167271 (C4 (Web Text))

Max Activating Token Index: 540