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

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

Neuron 5106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2229. Min Range: -1.2229

Max Act: 1.2229. Min Act: -0.0002

Data Index: 826639 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.9764. Min Act: -0.0002

Data Index: 1117835 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7700. Min Act: -0.0002

Data Index: 1018851 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8862. Min Act: -0.0002

Data Index: 1261395 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7836. Min Act: -0.0002

Data Index: 423648 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8847. Min Act: -0.0002

Data Index: 1242705 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8497. Min Act: -0.0002

Data Index: 823798 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8595. Min Act: -0.0002

Data Index: 302284 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8178. Min Act: -0.0002

Data Index: 677702 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7555. Min Act: -0.0002

Data Index: 132773 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.6208. Min Act: -0.0002

Data Index: 755492 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8511. Min Act: -0.0002

Data Index: 701351 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7967. Min Act: -0.0002

Data Index: 1234207 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.6924. Min Act: -0.0002

Data Index: 460276 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8163. Min Act: -0.0002

Data Index: 932669 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7716. Min Act: -0.0002

Data Index: 384117 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.7395. Min Act: -0.0002

Data Index: 187860 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8046. Min Act: -0.0002

Data Index: 169856 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.8089. Min Act: -0.0002

Data Index: 974251 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.2229. Min Range: -1.2229

Max Act: 0.6904. Min Act: -0.0002

Data Index: 936896 (C4 (Web Text))

Max Activating Token Index: 967