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

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

Neuron 1462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.6390. Min Act: -0.0000

Data Index: 853035 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1052321 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.4053. Min Act: -0.0000

Data Index: 144399 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3780. Min Act: -0.0000

Data Index: 990424 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3603. Min Act: -0.0000

Data Index: 131148 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3651. Min Act: -0.0000

Data Index: 127717 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3718. Min Act: -0.0000

Data Index: 919532 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3654. Min Act: -0.0000

Data Index: 186931 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1334319 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1295130 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1006272 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2879. Min Act: -0.0000

Data Index: 768529 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2675. Min Act: -0.0000

Data Index: 44907 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2894. Min Act: -0.0000

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1083960 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2762. Min Act: -0.0000

Data Index: 999626 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.3029. Min Act: -0.0000

Data Index: 57400 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2624. Min Act: -0.0000

Data Index: 347774 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2845. Min Act: -0.0000

Data Index: 904900 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.6390. Min Range: -0.6390

Max Act: 0.2648. Min Act: -0.0000

Data Index: 86618 (C4 (Web Text))

Max Activating Token Index: 791