Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3925 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2055. Min Act: -0.0000

Data Index: 471674 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1750. Min Act: -0.0000

Data Index: 666529 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1205063 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1686. Min Act: -0.0000

Data Index: 762783 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1805. Min Act: -0.0000

Data Index: 439456 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1584. Min Act: -0.0000

Data Index: 237907 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1500. Min Act: -0.0000

Data Index: 683200 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1643. Min Act: -0.0000

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1649. Min Act: -0.0000

Data Index: 190590 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1729. Min Act: -0.0000

Data Index: 710141 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1494. Min Act: -0.0000

Data Index: 44168 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1610. Min Act: -0.0000

Data Index: 423993 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1439. Min Act: -0.0000

Data Index: 422365 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1352012 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1393. Min Act: -0.0000

Data Index: 683197 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1472. Min Act: -0.0000

Data Index: 732018 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1410. Min Act: -0.0000

Data Index: 570574 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1010947 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1086997 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1522. Min Act: -0.0000

Data Index: 385660 (C4 (Web Text))

Max Activating Token Index: 947