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

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

Neuron 4247 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.1155. Min Act: -0.0000

Data Index: 755623 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.1719. Min Act: -0.0000

Data Index: 887121 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0313. Min Act: -0.0000

Data Index: 290144 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0526. Min Act: -0.0000

Data Index: 1032668 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8521. Min Act: -0.0000

Data Index: 801591 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1078150 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8399. Min Act: -0.0000

Data Index: 267121 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8179. Min Act: -0.0000

Data Index: 977036 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8008. Min Act: -0.0000

Data Index: 87359 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7453. Min Act: -0.0000

Data Index: 482239 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7516. Min Act: -0.0000

Data Index: 794091 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1044748 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7474. Min Act: -0.0000

Data Index: 609816 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7863. Min Act: -0.0000

Data Index: 574858 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7365. Min Act: -0.0000

Data Index: 545981 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7029. Min Act: -0.0000

Data Index: 971261 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1306236 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1048617 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1079830 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.6179. Min Act: -0.0000

Data Index: 298193 (C4 (Web Text))

Max Activating Token Index: 239