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

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

Neuron 3248 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.4498. Min Act: -0.0000

Data Index: 1601217 (Python Code)

Max Activating Token Index: 940

Text #1

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.1412. Min Act: 0.0000

Data Index: 558416 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.1947. Min Act: -0.0000

Data Index: 994515 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1370817 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1227582 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0174. Min Act: -0.0000

Data Index: 1352960 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1525150 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1269606 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1091826 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1503481 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0672. Min Act: -0.0000

Data Index: 1585000 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1044828 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1507333 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0477. Min Act: -0.0000

Data Index: 398075 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.4498. Min Range: -1.4498

Max Act: 1.0034. Min Act: 0.0000

Data Index: 1603670 (Python Code)

Max Activating Token Index: 869

Text #15

Max Range: 1.4498. Min Range: -1.4498

Max Act: 0.9551. Min Act: -0.0000

Data Index: 29173 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.4498. Min Range: -1.4498

Max Act: 0.9881. Min Act: -0.0000

Data Index: 944120 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.4498. Min Range: -1.4498

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1445713 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.4498. Min Range: -1.4498

Max Act: 0.9623. Min Act: -0.0000

Data Index: 41367 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.4498. Min Range: -1.4498

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1652474 (Python Code)

Max Activating Token Index: 689