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

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

Neuron 3172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1298016 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0746. Min Act: -0.0000

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0730. Min Act: -0.0000

Data Index: 521568 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1280213 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0586. Min Act: -0.0000

Data Index: 810665 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1237792 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0595. Min Act: -0.0000

Data Index: 291437 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0627. Min Act: -0.0000

Data Index: 21826 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0621. Min Act: -0.0000

Data Index: 847247 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0502. Min Act: -0.0000

Data Index: 708557 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1105472 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1358555 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0558. Min Act: -0.0000

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1157992 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0564. Min Act: -0.0000

Data Index: 14377 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0564. Min Act: -0.0000

Data Index: 974996 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0548. Min Act: -0.0001

Data Index: 506733 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0589. Min Act: -0.0000

Data Index: 512881 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0568. Min Act: -0.0000

Data Index: 1097561 (C4 (Web Text))

Max Activating Token Index: 423