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

Dataset: The Pile

Neuron 3920 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.6399. Min Act: -0.0000

Data Index: 1300763 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1606717 (The Pile)

Max Activating Token Index: 876

Text #2

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1077927 (The Pile)

Max Activating Token Index: 487

Text #3

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1012435 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1503098 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1866475 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1183522 (The Pile)

Max Activating Token Index: 869

Text #7

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4928. Min Act: -0.0000

Data Index: 855267 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1222439 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1513514 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1306631 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1071140 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4323. Min Act: -0.0000

Data Index: 428470 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1752264 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.3721. Min Act: -0.0000

Data Index: 747617 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4289. Min Act: -0.0000

Data Index: 598013 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1033468 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4045. Min Act: -0.0000

Data Index: 645596 (The Pile)

Max Activating Token Index: 499

Text #18

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4030. Min Act: -0.0000

Data Index: 182679 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4182. Min Act: -0.0000

Data Index: 139917 (The Pile)

Max Activating Token Index: 452