Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1854. Min Range: -3.1854

Max Act: 3.1854. Min Act: -0.0001

Data Index: 96729 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 3.1854. Min Range: -3.1854

Max Act: 3.0991. Min Act: -0.0000

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.8477. Min Act: -0.0001

Data Index: 1006596 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.3239. Min Act: -0.0000

Data Index: 329692 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.3657. Min Act: -0.0000

Data Index: 129981 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.3403. Min Act: -0.0000

Data Index: 1353611 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.3018. Min Act: -0.0001

Data Index: 797062 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1125185 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.1824. Min Act: -0.0000

Data Index: 95153 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.0395. Min Act: -0.0000

Data Index: 923164 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.0742. Min Act: -0.0000

Data Index: 421710 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.0566. Min Act: -0.0000

Data Index: 1050927 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.1854. Min Range: -3.1854

Max Act: 1.9320. Min Act: -0.0000

Data Index: 549185 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.1123. Min Act: -0.0001

Data Index: 627567 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.0833. Min Act: -0.0000

Data Index: 1045371 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 3.1854. Min Range: -3.1854

Max Act: 1.9910. Min Act: -0.0000

Data Index: 678011 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.1854. Min Range: -3.1854

Max Act: 2.0930. Min Act: -0.0000

Data Index: 1083141 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.1854. Min Range: -3.1854

Max Act: 1.7813. Min Act: -0.0000

Data Index: 1333281 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 3.1854. Min Range: -3.1854

Max Act: 1.7891. Min Act: -0.0001

Data Index: 693449 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 3.1854. Min Range: -3.1854

Max Act: 1.7681. Min Act: -0.0000

Data Index: 267442 (C4 (Web Text))

Max Activating Token Index: 1004