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

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

Neuron 915 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: 1.1820. Min Range: -1.1820

Max Act: 1.1820. Min Act: -0.0001

Data Index: 315316 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.0011. Min Act: -0.0001

Data Index: 1038447 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9829. Min Act: -0.0001

Data Index: 823208 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.1820. Min Range: -1.1820

Max Act: 1.1154. Min Act: -0.0001

Data Index: 1136888 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8955. Min Act: -0.0001

Data Index: 417220 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9872. Min Act: -0.0001

Data Index: 649316 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.9414. Min Act: -0.0001

Data Index: 1208470 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8266. Min Act: -0.0001

Data Index: 906299 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8263. Min Act: -0.0001

Data Index: 653103 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7810. Min Act: -0.0001

Data Index: 488216 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8106. Min Act: -0.0001

Data Index: 382054 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8012. Min Act: -0.0001

Data Index: 870017 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8457. Min Act: -0.0001

Data Index: 35157 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8017. Min Act: -0.0001

Data Index: 129833 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7618. Min Act: -0.0001

Data Index: 460070 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7482. Min Act: -0.0001

Data Index: 176462 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7644. Min Act: -0.0001

Data Index: 94722 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.8297. Min Act: -0.0001

Data Index: 185580 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7232. Min Act: -0.0001

Data Index: 279645 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.1820. Min Range: -1.1820

Max Act: 0.7120. Min Act: -0.0001

Data Index: 885208 (C4 (Web Text))

Max Activating Token Index: 830