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

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

Neuron 3146 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1275878 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1366282 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1266764 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9494. Min Act: -0.0000

Data Index: 664824 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9103. Min Act: -0.0000

Data Index: 908732 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9593. Min Act: -0.0000

Data Index: 336674 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9362. Min Act: -0.0000

Data Index: 41384 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9063. Min Act: -0.0000

Data Index: 683621 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1100478 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7790. Min Act: -0.0000

Data Index: 458412 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1551480 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7742. Min Act: -0.0000

Data Index: 501099 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7054. Min Act: -0.0000

Data Index: 603573 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7465. Min Act: -0.0000

Data Index: 249012 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7766. Min Act: -0.0000

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7646. Min Act: -0.0000

Data Index: 695526 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7245. Min Act: -0.0000

Data Index: 984291 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7303. Min Act: -0.0000

Data Index: 116030 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1119156 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1268604 (C4 (Web Text))

Max Activating Token Index: 187