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

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

Neuron 1372 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0039. Min Act: -0.0000

Data Index: 310105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.3002. Min Act: -0.0000

Data Index: 304461 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0991. Min Act: -0.0000

Data Index: 666366 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0298. Min Act: -0.0000

Data Index: 709318 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0784. Min Act: -0.0000

Data Index: 770743 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0771. Min Act: -0.0000

Data Index: 765016 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.1007. Min Act: -0.0000

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0660. Min Act: -0.0000

Data Index: 587154 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1513549 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1372822 (Python Code)

Max Activating Token Index: 746

Text #10

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1280945 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0713. Min Act: -0.0000

Data Index: 596307 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0671. Min Act: -0.0000

Data Index: 907415 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1252 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1123398 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1186286 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1627666 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0568. Min Act: -0.0000

Data Index: 933186 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0493. Min Act: -0.0000

Data Index: 20138 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3002. Min Range: -0.3002

Max Act: 0.0674. Min Act: -0.0000

Data Index: 852450 (C4 (Web Text))

Max Activating Token Index: 735