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

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

Neuron 569 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1145062 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0676. Min Act: -0.0002

Data Index: 637168 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0655. Min Act: -0.0002

Data Index: 120577 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1336185 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0644. Min Act: -0.0002

Data Index: 538948 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1174055 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1234186 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0626. Min Act: -0.0002

Data Index: 502833 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1203736 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0643. Min Act: -0.0002

Data Index: 898079 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1266652 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0608. Min Act: -0.0002

Data Index: 604660 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0580. Min Act: -0.0002

Data Index: 936620 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1361074 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0584. Min Act: -0.0002

Data Index: 500539 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1060654 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0563. Min Act: -0.0002

Data Index: 501375 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0566. Min Act: -0.0002

Data Index: 974252 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0619. Min Act: -0.0002

Data Index: 472034 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1323987 (C4 (Web Text))

Max Activating Token Index: 278