Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 369 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6062. Min Act: -0.0003

Data Index: 148447 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.7163. Min Act: -0.0003

Data Index: 581307 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4411. Min Act: -0.0003

Data Index: 696656 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.6278. Min Act: -0.0003

Data Index: 1255296 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4620. Min Act: -0.0003

Data Index: 921605 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.0879. Min Act: -0.0004

Data Index: 285261 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.3282. Min Act: -0.0003

Data Index: 379185 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4435. Min Act: -0.0003

Data Index: 801709 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.0750. Min Act: -0.0004

Data Index: 1056619 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4577. Min Act: -0.0003

Data Index: 1321219 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4513. Min Act: -0.0003

Data Index: 1258299 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.1807. Min Act: -0.0004

Data Index: 999510 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4008. Min Act: -0.0003

Data Index: 821220 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.2634. Min Act: -0.0003

Data Index: 9846 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4910. Min Act: -0.0003

Data Index: 1214323 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.4062. Min Act: -0.0003

Data Index: 1063453 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.0159. Min Act: -0.0003

Data Index: 1189956 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.3687. Min Act: -0.0003

Data Index: 1226059 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.2751. Min Act: -0.0003

Data Index: 194134 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 1.7163. Min Range: -1.7163

Max Act: 1.3174. Min Act: -0.0003

Data Index: 390770 (C4 (Web Text))

Max Activating Token Index: 509