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

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

Neuron 155 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: 0.6314. Min Range: -0.6314

Max Act: 0.6009. Min Act: -0.0003

Data Index: 350025 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5902. Min Act: -0.0003

Data Index: 840555 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.6031. Min Act: -0.0003

Data Index: 886728 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.6314. Min Act: -0.0003

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.6059. Min Act: -0.0003

Data Index: 1826 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5923. Min Act: -0.0003

Data Index: 298131 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5805. Min Act: -0.0003

Data Index: 894873 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5757. Min Act: -0.0003

Data Index: 391498 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5579. Min Act: -0.0004

Data Index: 1093863 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5674. Min Act: -0.0003

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5643. Min Act: -0.0003

Data Index: 453292 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5758. Min Act: -0.0003

Data Index: 1069982 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5524. Min Act: -0.0003

Data Index: 212327 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5709. Min Act: -0.0003

Data Index: 167380 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5433. Min Act: -0.0003

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4744. Min Act: -0.0003

Data Index: 233902 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.4885. Min Act: -0.0003

Data Index: 559874 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5356. Min Act: -0.0003

Data Index: 1280781 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5332. Min Act: -0.0003

Data Index: 950987 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.6314. Min Range: -0.6314

Max Act: 0.5091. Min Act: -0.0003

Data Index: 808910 (C4 (Web Text))

Max Activating Token Index: 102