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

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

Neuron 1918 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.9113. Min Act: -0.0000

Data Index: 413855 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 2.1158. Min Range: -2.1158

Max Act: 2.1158. Min Act: -0.0000

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.9878. Min Act: -0.0000

Data Index: 621565 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.7963. Min Act: -0.0000

Data Index: 43521 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.6137. Min Act: -0.0000

Data Index: 1012688 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.4881. Min Act: -0.0000

Data Index: 341087 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.2976. Min Act: -0.0000

Data Index: 27954 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.5123. Min Act: -0.0000

Data Index: 179661 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.2775. Min Act: -0.0000

Data Index: 271790 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.2492. Min Act: -0.0000

Data Index: 663945 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.1556. Min Act: -0.0000

Data Index: 229460 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.0173. Min Act: -0.0000

Data Index: 759570 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.0794. Min Act: -0.0000

Data Index: 230378 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.1236. Min Act: -0.0000

Data Index: 13127 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.1019. Min Act: -0.0000

Data Index: 958750 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 2.1158. Min Range: -2.1158

Max Act: 0.9775. Min Act: -0.0000

Data Index: 908743 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 2.1158. Min Range: -2.1158

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1265052 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.1158. Min Range: -2.1158

Max Act: 1.1685. Min Act: -0.0000

Data Index: 875796 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.1158. Min Range: -2.1158

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1052821 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.1158. Min Range: -2.1158

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1388426 (Python Code)

Max Activating Token Index: 43