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

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

Neuron 4732 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: 0.6806. Min Range: -0.6806

Max Act: 0.6806. Min Act: -0.0000

Data Index: 690781 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1319592 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1037892 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5843. Min Act: -0.0000

Data Index: 617945 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6209. Min Act: -0.0000

Data Index: 139917 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5698. Min Act: -0.0000

Data Index: 334113 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4891. Min Act: -0.0000

Data Index: 333373 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5244. Min Act: -0.0000

Data Index: 263897 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1210541 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1117993 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4836. Min Act: -0.0000

Data Index: 762874 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5459. Min Act: -0.0000

Data Index: 450409 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5001. Min Act: -0.0000

Data Index: 96834 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5443. Min Act: -0.0000

Data Index: 40262 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4757. Min Act: -0.0000

Data Index: 572475 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4222. Min Act: -0.0000

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4385. Min Act: -0.0000

Data Index: 934176 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4614. Min Act: -0.0000

Data Index: 78943 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4564. Min Act: -0.0000

Data Index: 384831 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4619. Min Act: -0.0000

Data Index: 326115 (C4 (Web Text))

Max Activating Token Index: 266