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

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

Neuron 5035 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: 1.4159. Min Range: -1.4159

Max Act: 1.2914. Min Act: -0.0000

Data Index: 827544 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.2024. Min Act: -0.0000

Data Index: 482271 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.4159. Min Act: -0.0000

Data Index: 859474 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1664. Min Act: -0.0000

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1015344 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.0242. Min Act: -0.0000

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1150. Min Act: -0.0000

Data Index: 583914 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.0074. Min Act: -0.0000

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1654. Min Act: -0.0000

Data Index: 317232 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.0846. Min Act: -0.0000

Data Index: 435682 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1063521 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.9955. Min Act: -0.0000

Data Index: 397905 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.8751. Min Act: -0.0000

Data Index: 28972 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.0213. Min Act: -0.0000

Data Index: 686223 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.9575. Min Act: -0.0000

Data Index: 835308 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.1384. Min Act: -0.0000

Data Index: 985493 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.9243. Min Act: -0.0000

Data Index: 20206 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.9470. Min Act: -0.0000

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.4159. Min Range: -1.4159

Max Act: 1.0349. Min Act: -0.0000

Data Index: 336083 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.4159. Min Range: -1.4159

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1353153 (C4 (Web Text))

Max Activating Token Index: 781