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

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

Neuron 2881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.2147. Min Act: -0.0000

Data Index: 236653 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.1202. Min Act: -0.0000

Data Index: 1260088 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.1154. Min Act: -0.0000

Data Index: 445590 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.0156. Min Act: -0.0000

Data Index: 531075 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.1891. Min Act: -0.0000

Data Index: 234843 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.9553. Min Act: -0.0000

Data Index: 958595 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.9485. Min Act: -0.0000

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.0421. Min Act: -0.0000

Data Index: 679051 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 2.2147. Min Range: -2.2147

Max Act: 2.0294. Min Act: -0.0000

Data Index: 966682 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.8212. Min Act: -0.0000

Data Index: 960055 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7797. Min Act: -0.0000

Data Index: 497496 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1151207 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7749. Min Act: -0.0000

Data Index: 798797 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7387. Min Act: -0.0000

Data Index: 1012133 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7245. Min Act: -0.0000

Data Index: 1296753 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.6163. Min Act: -0.0000

Data Index: 560400 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7131. Min Act: -0.0000

Data Index: 967744 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.7011. Min Act: -0.0000

Data Index: 1123667 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.5610. Min Act: -0.0000

Data Index: 871091 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 2.2147. Min Range: -2.2147

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1162849 (C4 (Web Text))

Max Activating Token Index: 110