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

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

Neuron 1089 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1066. Min Range: -1.1066

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1297372 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8218. Min Act: -0.0000

Data Index: 942112 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1279504 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.8102. Min Act: -0.0000

Data Index: 879030 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1081589 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.7714. Min Act: 0.0000

Data Index: 1049297 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6759. Min Act: -0.0000

Data Index: 754114 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6643. Min Act: -0.0000

Data Index: 120475 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6124. Min Act: -0.0000

Data Index: 173316 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6116. Min Act: -0.0000

Data Index: 892203 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5903. Min Act: -0.0000

Data Index: 737056 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5993. Min Act: 0.0000

Data Index: 441016 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6162. Min Act: -0.0000

Data Index: 101046 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5960. Min Act: -0.0000

Data Index: 465541 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5815. Min Act: -0.0000

Data Index: 184336 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5739. Min Act: -0.0000

Data Index: 375948 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5636. Min Act: -0.0000

Data Index: 325016 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5435. Min Act: -0.0000

Data Index: 615046 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.5581. Min Act: -0.0000

Data Index: 606665 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.1066. Min Range: -1.1066

Max Act: 0.6043. Min Act: -0.0000

Data Index: 317105 (C4 (Web Text))

Max Activating Token Index: 288