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

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

Neuron 3857 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.4002. Min Act: -0.0001

Data Index: 548021 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.2842. Min Act: -0.0001

Data Index: 458548 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1598. Min Act: -0.0001

Data Index: 67194 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0748. Min Act: -0.0001

Data Index: 104260 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1645. Min Act: -0.0001

Data Index: 517456 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1160551 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1266706 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1625. Min Act: -0.0001

Data Index: 20180 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0659. Min Act: -0.0001

Data Index: 651259 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1069. Min Act: -0.0001

Data Index: 486376 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0004. Min Act: -0.0001

Data Index: 179661 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0738. Min Act: -0.0001

Data Index: 634138 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0412. Min Act: -0.0001

Data Index: 686561 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9762. Min Act: -0.0001

Data Index: 1357659 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0019. Min Act: -0.0001

Data Index: 1306546 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9510. Min Act: -0.0001

Data Index: 663945 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.0051. Min Act: -0.0001

Data Index: 1117429 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9902. Min Act: -0.0001

Data Index: 854816 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9886. Min Act: -0.0001

Data Index: 52362 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9836. Min Act: -0.0001

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 206