Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7398. Min Act: -0.0002

Data Index: 851013 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.9603. Min Act: -0.0001

Data Index: 1112594 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7866. Min Act: -0.0001

Data Index: 1117645 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6968. Min Act: -0.0002

Data Index: 678229 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.8245. Min Act: -0.0001

Data Index: 343183 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.8747. Min Act: -0.0002

Data Index: 1289425 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7841. Min Act: -0.0002

Data Index: 64017 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7647. Min Act: -0.0001

Data Index: 1331928 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7512. Min Act: -0.0002

Data Index: 919201 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7228. Min Act: -0.0001

Data Index: 172905 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7849. Min Act: -0.0001

Data Index: 1310300 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7432. Min Act: -0.0001

Data Index: 643622 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7433. Min Act: -0.0002

Data Index: 796317 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7623. Min Act: -0.0002

Data Index: 1085355 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7150. Min Act: -0.0001

Data Index: 588782 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7130. Min Act: -0.0001

Data Index: 993831 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6065. Min Act: -0.0001

Data Index: 807549 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6918. Min Act: -0.0002

Data Index: 584678 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6438. Min Act: -0.0001

Data Index: 1236319 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6291. Min Act: -0.0001

Data Index: 1311484 (C4 (Web Text))

Max Activating Token Index: 171