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

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

Neuron 3552 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: 3.8343. Min Range: -3.8343

Max Act: 3.8343. Min Act: -0.0001

Data Index: 1284987 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 3.8343. Min Range: -3.8343

Max Act: 3.7756. Min Act: -0.0001

Data Index: 251473 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 3.8343. Min Range: -3.8343

Max Act: 3.6975. Min Act: -0.0001

Data Index: 702913 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.8343. Min Range: -3.8343

Max Act: 3.5235. Min Act: -0.0000

Data Index: 1178720 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 3.8343. Min Range: -3.8343

Max Act: 3.3244. Min Act: -0.0001

Data Index: 563512 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.9243. Min Act: -0.0001

Data Index: 264155 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.8691. Min Act: -0.0001

Data Index: 404304 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.5531. Min Act: -0.0001

Data Index: 1055201 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.6564. Min Act: -0.0001

Data Index: 642507 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.2734. Min Act: -0.0000

Data Index: 419887 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.5181. Min Act: -0.0001

Data Index: 1240084 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.2443. Min Act: -0.0001

Data Index: 893210 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.4672. Min Act: -0.0000

Data Index: 13113 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.4649. Min Act: -0.0001

Data Index: 1175631 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.4632. Min Act: -0.0001

Data Index: 1087233 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.5666. Min Act: -0.0001

Data Index: 656725 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.4157. Min Act: -0.0001

Data Index: 427086 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.2821. Min Act: -0.0001

Data Index: 548161 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.3507. Min Act: -0.0001

Data Index: 560575 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 3.8343. Min Range: -3.8343

Max Act: 2.2158. Min Act: -0.0001

Data Index: 922580 (C4 (Web Text))

Max Activating Token Index: 421