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

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

Neuron 1912 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1155009 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.1407. Min Act: -0.0000

Data Index: 349018 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9881. Min Act: -0.0000

Data Index: 1173188 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0808. Min Act: -0.0000

Data Index: 999476 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0968. Min Act: -0.0000

Data Index: 276698 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1044241 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0244. Min Act: -0.0000

Data Index: 453564 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9065. Min Act: -0.0000

Data Index: 531943 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9820. Min Act: -0.0000

Data Index: 927339 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1061586 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0586. Min Act: -0.0000

Data Index: 714813 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0306. Min Act: -0.0000

Data Index: 856503 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0232. Min Act: -0.0000

Data Index: 776998 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9961. Min Act: -0.0000

Data Index: 790910 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1322005 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9595. Min Act: -0.0000

Data Index: 112974 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9511. Min Act: -0.0000

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0907. Min Act: -0.0000

Data Index: 656320 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 1.1407. Min Range: -1.1407

Max Act: 1.0777. Min Act: -0.0000

Data Index: 303181 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 1.1407. Min Range: -1.1407

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1012206 (C4 (Web Text))

Max Activating Token Index: 848