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

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

Neuron 331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.5262. Min Act: -0.0001

Data Index: 447565 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1094519 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1045897 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.4012. Min Act: -0.0001

Data Index: 1385120 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3809. Min Act: -0.0001

Data Index: 98743 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1470401 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1109671 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3702. Min Act: -0.0001

Data Index: 965397 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3170. Min Act: -0.0001

Data Index: 387027 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3476. Min Act: -0.0001

Data Index: 948531 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3849. Min Act: -0.0001

Data Index: 1347639 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1593816 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3008. Min Act: -0.0001

Data Index: 706089 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3141. Min Act: -0.0001

Data Index: 27030 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1301849 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3384. Min Act: -0.0001

Data Index: 220759 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3084. Min Act: -0.0001

Data Index: 1282824 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3432. Min Act: -0.0001

Data Index: 679060 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3087. Min Act: -0.0001

Data Index: 1170074 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.5262. Min Range: -0.5262

Max Act: 0.3185. Min Act: -0.0001

Data Index: 350477 (C4 (Web Text))

Max Activating Token Index: 38