Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 583 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0003

Data Index: 1492295 (Python Code)

Max Activating Token Index: 853

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1132. Min Act: -0.0003

Data Index: 1652188 (Python Code)

Max Activating Token Index: 455

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1405390 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1454744 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1429723 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1606703 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1637551 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1371249 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1656685 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1630730 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1379879 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1570280 (Python Code)

Max Activating Token Index: 370

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1655440 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1391497 (Python Code)

Max Activating Token Index: 781

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1483328 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1539115 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0489. Min Act: -0.0003

Data Index: 1535151 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1415772 (Python Code)

Max Activating Token Index: 246

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1575928 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1594304 (Python Code)

Max Activating Token Index: 519