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

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

Neuron 1535 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5413. Min Range: -1.5413

Max Act: 1.5413. Min Act: -0.0000

Data Index: 32400 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.5413. Min Range: -1.5413

Max Act: 1.3117. Min Act: -0.0000

Data Index: 497354 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.9903. Min Act: -0.0000

Data Index: 925375 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.8287. Min Act: -0.0000

Data Index: 512622 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.9132. Min Act: -0.0000

Data Index: 229598 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.7905. Min Act: -0.0000

Data Index: 987012 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.7377. Min Act: -0.0000

Data Index: 331801 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.7162. Min Act: -0.0000

Data Index: 645778 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.7663. Min Act: -0.0000

Data Index: 239913 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1273799 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6373. Min Act: -0.0000

Data Index: 18075 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.5589. Min Act: -0.0000

Data Index: 338562 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6092. Min Act: -0.0000

Data Index: 215863 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.5986. Min Act: -0.0000

Data Index: 660399 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6196. Min Act: -0.0000

Data Index: 473493 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.5497. Min Act: -0.0000

Data Index: 611538 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1146175 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1069829 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1257439 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.5413. Min Range: -1.5413

Max Act: 0.6942. Min Act: -0.0000

Data Index: 607465 (C4 (Web Text))

Max Activating Token Index: 586