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

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

Neuron 3566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1640. Min Range: -3.1640

Max Act: 3.1640. Min Act: -0.0000

Data Index: 127232 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.7300. Min Act: -0.0000

Data Index: 1150068 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.8557. Min Act: -0.0000

Data Index: 365882 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.8197. Min Act: -0.0000

Data Index: 434151 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.3392. Min Act: -0.0000

Data Index: 1335309 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1243361 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.8495. Min Act: -0.0000

Data Index: 906119 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.2654. Min Act: -0.0000

Data Index: 924583 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.2322. Min Act: -0.0000

Data Index: 1567956 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.4624. Min Act: -0.0000

Data Index: 54109 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.4330. Min Act: -0.0000

Data Index: 205700 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.0868. Min Act: -0.0000

Data Index: 842655 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.4183. Min Act: -0.0000

Data Index: 789105 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.4074. Min Act: -0.0000

Data Index: 1059444 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.3263. Min Act: -0.0000

Data Index: 705777 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.3133. Min Act: -0.0000

Data Index: 193583 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.2815. Min Act: -0.0000

Data Index: 883015 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.1363. Min Act: -0.0000

Data Index: 635558 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 3.1640. Min Range: -3.1640

Max Act: 2.2516. Min Act: -0.0000

Data Index: 632552 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 3.1640. Min Range: -3.1640

Max Act: 1.9068. Min Act: -0.0000

Data Index: 507841 (C4 (Web Text))

Max Activating Token Index: 572