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

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

Neuron 2059 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.5873. Min Act: -0.0001

Data Index: 454305 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.3461. Min Act: -0.0001

Data Index: 756870 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.5315. Min Act: -0.0001

Data Index: 406433 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.4469. Min Act: -0.0001

Data Index: 1245466 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.3453. Min Act: -0.0001

Data Index: 160480 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.9593. Min Act: -0.0001

Data Index: 553522 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.8908. Min Act: -0.0001

Data Index: 651359 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.1017. Min Act: -0.0001

Data Index: 1152833 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.8218. Min Act: -0.0001

Data Index: 39440 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.7872. Min Act: -0.0001

Data Index: 1168456 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.7673. Min Act: -0.0001

Data Index: 68412 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.5618. Min Act: -0.0001

Data Index: 725849 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.9014. Min Act: -0.0001

Data Index: 1012465 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.9937. Min Act: -0.0001

Data Index: 87634 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.4223. Min Act: -0.0001

Data Index: 234750 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.9760. Min Act: -0.0001

Data Index: 1087299 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.5692. Min Act: -0.0001

Data Index: 1340531 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.2925. Min Act: -0.0001

Data Index: 205507 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.9353. Min Act: -0.0001

Data Index: 1243332 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.1745. Min Act: -0.0001

Data Index: 292849 (C4 (Web Text))

Max Activating Token Index: 63