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

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

Neuron 1770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2160. Min Act: -0.0000

Data Index: 235484 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1137177 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1207554 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.2108. Min Act: -0.0000

Data Index: 918479 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1978. Min Act: -0.0000

Data Index: 72829 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1947. Min Act: -0.0000

Data Index: 653718 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1230060 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1755. Min Act: -0.0000

Data Index: 854605 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1117361 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1698. Min Act: -0.0000

Data Index: 34947 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1813. Min Act: 0.0000

Data Index: 340884 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1581. Min Act: -0.0000

Data Index: 308302 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1222325 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1566. Min Act: -0.0000

Data Index: 978403 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1563. Min Act: -0.0000

Data Index: 2196 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1611. Min Act: -0.0000

Data Index: 56290 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1506. Min Act: -0.0000

Data Index: 507603 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1547. Min Act: -0.0000

Data Index: 953101 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1474. Min Act: -0.0000

Data Index: 140809 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2160. Min Range: -0.2160

Max Act: 0.1468. Min Act: 0.0001

Data Index: 362420 (C4 (Web Text))

Max Activating Token Index: 43