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

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

Neuron 4536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2628. Min Range: -2.2628

Max Act: 2.2628. Min Act: -0.0000

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 2.2628. Min Range: -2.2628

Max Act: 2.0154. Min Act: -0.0000

Data Index: 737578 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.9044. Min Act: -0.0000

Data Index: 1303271 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.8298. Min Act: -0.0000

Data Index: 1130446 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.8038. Min Act: -0.0000

Data Index: 617424 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.9936. Min Act: -0.0000

Data Index: 44567 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.6798. Min Act: -0.0000

Data Index: 472260 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.7147. Min Act: -0.0000

Data Index: 187351 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.6540. Min Act: -0.0000

Data Index: 699463 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.7986. Min Act: -0.0000

Data Index: 225776 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1102161 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.5745. Min Act: -0.0000

Data Index: 168157 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1116917 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.7066. Min Act: -0.0000

Data Index: 976490 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.5541. Min Act: -0.0000

Data Index: 464205 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.2780. Min Act: -0.0000

Data Index: 128122 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.5482. Min Act: -0.0000

Data Index: 165293 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.4983. Min Act: -0.0000

Data Index: 259224 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.5124. Min Act: -0.0000

Data Index: 102970 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 2.2628. Min Range: -2.2628

Max Act: 1.4462. Min Act: -0.0000

Data Index: 1130029 (C4 (Web Text))

Max Activating Token Index: 462