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

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

Neuron 5027 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.4646. Min Act: -0.0000

Data Index: 1003311 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.5218. Min Act: -0.0000

Data Index: 758078 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.5146. Min Act: -0.0000

Data Index: 688681 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.1691. Min Act: -0.0000

Data Index: 462777 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.2667. Min Act: -0.0000

Data Index: 570200 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.0116. Min Act: -0.0000

Data Index: 651996 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.1239. Min Act: -0.0000

Data Index: 964698 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.2043. Min Act: -0.0000

Data Index: 976200 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.1840. Min Act: -0.0000

Data Index: 938410 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.9367. Min Act: -0.0000

Data Index: 318490 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 2.5218. Min Range: -2.5218

Max Act: 2.0583. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.9250. Min Act: -0.0000

Data Index: 75815 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.9152. Min Act: -0.0000

Data Index: 980290 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.9059. Min Act: -0.0000

Data Index: 526046 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.8959. Min Act: -0.0000

Data Index: 55985 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.8286. Min Act: -0.0000

Data Index: 73952 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.7205. Min Act: -0.0000

Data Index: 566146 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.7091. Min Act: -0.0000

Data Index: 527563 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.7120. Min Act: -0.0000

Data Index: 196594 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 2.5218. Min Range: -2.5218

Max Act: 1.6692. Min Act: -0.0000

Data Index: 901450 (C4 (Web Text))

Max Activating Token Index: 589