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

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

Neuron 1856 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0188. Min Range: -1.0188

Max Act: 1.0188. Min Act: -0.0000

Data Index: 3909 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.9949. Min Act: -0.0000

Data Index: 940864 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1182214 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1201673 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.9140. Min Act: -0.0000

Data Index: 720601 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.8641. Min Act: -0.0000

Data Index: 331002 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1332273 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.8023. Min Act: -0.0000

Data Index: 574456 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7940. Min Act: -0.0000

Data Index: 593155 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7821. Min Act: -0.0000

Data Index: 635943 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7607. Min Act: -0.0000

Data Index: 1496496 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1076721 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1577446 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7876. Min Act: -0.0000

Data Index: 582400 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1232867 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1428158 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1312773 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1385769 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1424322 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 1.0188. Min Range: -1.0188

Max Act: 0.7281. Min Act: -0.0000

Data Index: 893125 (C4 (Web Text))

Max Activating Token Index: 886