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

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

Neuron 3014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1328. Min Range: -1.1328

Max Act: 1.1328. Min Act: -0.0000

Data Index: 749672 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9492. Min Act: -0.0001

Data Index: 772894 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9687. Min Act: -0.0000

Data Index: 604222 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9044. Min Act: -0.0000

Data Index: 452491 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1189470 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1149684 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.8174. Min Act: -0.0000

Data Index: 934511 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7624. Min Act: -0.0000

Data Index: 717627 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7768. Min Act: -0.0001

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7633. Min Act: -0.0000

Data Index: 506715 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7754. Min Act: -0.0001

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7189. Min Act: -0.0000

Data Index: 284220 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7648. Min Act: -0.0000

Data Index: 1236046 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7191. Min Act: -0.0000

Data Index: 237151 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7000. Min Act: -0.0000

Data Index: 456854 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7110. Min Act: -0.0001

Data Index: 359794 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7141. Min Act: -0.0001

Data Index: 448642 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7064. Min Act: -0.0001

Data Index: 284811 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.1328. Min Range: -1.1328

Max Act: 0.7037. Min Act: -0.0001

Data Index: 445499 (C4 (Web Text))

Max Activating Token Index: 948