Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5441 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1201. Min Act: -0.0002

Data Index: 670357 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1043. Min Act: -0.0002

Data Index: 684205 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1301557 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1320861 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0966. Min Act: -0.0002

Data Index: 646014 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0946. Min Act: -0.0002

Data Index: 917861 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1061936 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0891. Min Act: -0.0002

Data Index: 207516 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0896. Min Act: -0.0002

Data Index: 880488 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1312946 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0852. Min Act: -0.0002

Data Index: 669347 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1297026 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1214830 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0813. Min Act: -0.0002

Data Index: 641458 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0844. Min Act: -0.0002

Data Index: 373717 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1358373 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1356162 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0793. Min Act: -0.0002

Data Index: 481507 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0791. Min Act: -0.0002

Data Index: 187151 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.0771. Min Act: -0.0002

Data Index: 785710 (C4 (Web Text))

Max Activating Token Index: 847