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

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

Neuron 1089 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0002

Data Index: 237351 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0629. Min Act: -0.0002

Data Index: 233187 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1053295 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1060576 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0599. Min Act: -0.0002

Data Index: 215968 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0567. Min Act: -0.0002

Data Index: 221727 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0560. Min Act: -0.0002

Data Index: 724817 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0538. Min Act: -0.0002

Data Index: 531748 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1130302 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0510. Min Act: -0.0002

Data Index: 905653 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1291963 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0477. Min Act: -0.0002

Data Index: 189369 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0482. Min Act: -0.0002

Data Index: 691435 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0481. Min Act: -0.0002

Data Index: 754623 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0478. Min Act: -0.0002

Data Index: 934521 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0477. Min Act: -0.0002

Data Index: 433861 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0464. Min Act: -0.0002

Data Index: 774146 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0462. Min Act: -0.0002

Data Index: 146105 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0452. Min Act: -0.0002

Data Index: 567644 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1320280 (C4 (Web Text))

Max Activating Token Index: 156