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

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

Neuron 1403 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: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0000

Data Index: 742426 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1749. Min Act: -0.0000

Data Index: 979016 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1737. Min Act: -0.0000

Data Index: 485002 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1655. Min Act: -0.0000

Data Index: 395453 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1626. Min Act: -0.0000

Data Index: 502386 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1581. Min Act: 0.0000

Data Index: 285236 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1567. Min Act: -0.0000

Data Index: 287468 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1350035 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1050731 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1516. Min Act: 0.0000

Data Index: 250375 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1457. Min Act: -0.0001

Data Index: 314736 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1255179 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1491. Min Act: -0.0000

Data Index: 185711 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1489. Min Act: -0.0001

Data Index: 54624 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1482. Min Act: -0.0001

Data Index: 501040 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1110359 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1536. Min Act: -0.0000

Data Index: 319208 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1208272 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1223668 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1502. Min Act: -0.0000

Data Index: 858131 (C4 (Web Text))

Max Activating Token Index: 578