Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1800 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.5218. Min Act: -0.0001

Data Index: 1143145 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.6743. Min Act: -0.0000

Data Index: 1240738 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.6184. Min Act: -0.0000

Data Index: 763429 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.4772. Min Act: -0.0001

Data Index: 761703 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.6135. Min Act: -0.0001

Data Index: 935454 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.7465. Min Act: -0.0001

Data Index: 702711 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.5281. Min Act: -0.0001

Data Index: 764723 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.1057. Min Act: -0.0001

Data Index: 248490 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.3753. Min Act: -0.0001

Data Index: 1159035 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.0751. Min Act: -0.0001

Data Index: 595369 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.1705. Min Act: -0.0001

Data Index: 606648 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.9039. Min Act: -0.0001

Data Index: 1329748 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.0120. Min Act: -0.0001

Data Index: 773604 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.0175. Min Act: -0.0001

Data Index: 1109319 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.9722. Min Act: -0.0001

Data Index: 300121 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.0785. Min Act: -0.0001

Data Index: 1011593 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 3.7465. Min Range: -3.7465

Max Act: 3.0232. Min Act: -0.0001

Data Index: 17288 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.8956. Min Act: -0.0001

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.7526. Min Act: -0.0001

Data Index: 1080209 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 3.7465. Min Range: -3.7465

Max Act: 2.9775. Min Act: -0.0001

Data Index: 577861 (C4 (Web Text))

Max Activating Token Index: 95