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

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

Neuron 5695 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1304637 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8665. Min Act: -0.0000

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8962. Min Act: -0.0000

Data Index: 507021 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1256886 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8127. Min Act: -0.0000

Data Index: 824289 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8081. Min Act: -0.0000

Data Index: 779945 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7619. Min Act: -0.0000

Data Index: 473021 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1096519 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7870. Min Act: -0.0000

Data Index: 830268 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1285873 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7224. Min Act: -0.0000

Data Index: 885938 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1051537 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1198033 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1100576 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6980. Min Act: -0.0000

Data Index: 536658 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1289571 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1225125 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6682. Min Act: -0.0000

Data Index: 156411 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7119. Min Act: -0.0000

Data Index: 938402 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6615. Min Act: -0.0000

Data Index: 445784 (C4 (Web Text))

Max Activating Token Index: 906