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

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

Neuron 4989 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.3281. Min Act: -0.0001

Data Index: 678360 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.1516. Min Act: -0.0001

Data Index: 134211 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0037. Min Act: -0.0001

Data Index: 1089598 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0604. Min Act: -0.0001

Data Index: 25979 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9527. Min Act: -0.0001

Data Index: 494493 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8739. Min Act: -0.0001

Data Index: 1214784 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0278. Min Act: -0.0001

Data Index: 132400 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9684. Min Act: -0.0001

Data Index: 156793 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9842. Min Act: -0.0001

Data Index: 1155232 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9466. Min Act: -0.0001

Data Index: 11514 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9657. Min Act: -0.0001

Data Index: 138814 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9429. Min Act: -0.0001

Data Index: 80123 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9439. Min Act: -0.0001

Data Index: 165985 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9283. Min Act: -0.0001

Data Index: 1056416 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9427. Min Act: -0.0001

Data Index: 287418 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.9927. Min Act: -0.0001

Data Index: 687871 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8605. Min Act: -0.0001

Data Index: 1080704 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8961. Min Act: -0.0001

Data Index: 858523 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8631. Min Act: -0.0001

Data Index: 992331 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8766. Min Act: -0.0001

Data Index: 1163051 (C4 (Web Text))

Max Activating Token Index: 161