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

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

Neuron 170 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.8844. Min Act: -0.0000

Data Index: 1596163 (Python Code)

Max Activating Token Index: 240

Text #1

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1580472 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1108781 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1385890 (Python Code)

Max Activating Token Index: 933

Text #4

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1598113 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.3366. Min Act: -0.0000

Data Index: 1450055 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.2921. Min Act: -0.0000

Data Index: 297089 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1441832 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1373001 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.9476. Min Act: -0.0000

Data Index: 652809 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.1196. Min Act: -0.0000

Data Index: 229733 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.8844. Min Range: -1.8844

Max Act: 1.1062. Min Act: -0.0000

Data Index: 320957 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1334105 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1388452 (Python Code)

Max Activating Token Index: 546

Text #14

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1403401 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1530721 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1001875 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1554708 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1397071 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 1.8844. Min Range: -1.8844

Max Act: 0.8493. Min Act: -0.0000

Data Index: 42720 (C4 (Web Text))

Max Activating Token Index: 332