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

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

Neuron 3055 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5412. Min Act: -0.0000

Data Index: 11855 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1197633 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1152478 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4902. Min Act: -0.0000

Data Index: 818919 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4865. Min Act: -0.0000

Data Index: 340811 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5116. Min Act: -0.0000

Data Index: 569914 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4903. Min Act: -0.0000

Data Index: 360271 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4728. Min Act: -0.0000

Data Index: 958426 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4859. Min Act: -0.0000

Data Index: 128592 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1386877 (Python Code)

Max Activating Token Index: 261

Text #10

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4632. Min Act: -0.0000

Data Index: 74452 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1278067 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1062648 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4594. Min Act: -0.0000

Data Index: 206815 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4613. Min Act: -0.0000

Data Index: 258209 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4436. Min Act: -0.0000

Data Index: 887636 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4550. Min Act: -0.0000

Data Index: 298442 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.4732. Min Act: -0.0000

Data Index: 974002 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3980. Min Act: -0.0000

Data Index: 144524 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.5412. Min Range: -0.5412

Max Act: 0.3238. Min Act: -0.0000

Data Index: 577669 (C4 (Web Text))

Max Activating Token Index: 279