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

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

Neuron 2508 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: 0.5481. Min Range: -0.5481

Max Act: 0.5331. Min Act: 0.0002

Data Index: 1626759 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1427855 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5391. Min Act: 0.0002

Data Index: 1499095 (Python Code)

Max Activating Token Index: 789

Text #3

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.5481. Min Act: 0.0001

Data Index: 1468840 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4932. Min Act: 0.0000

Data Index: 1644816 (Python Code)

Max Activating Token Index: 556

Text #5

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4820. Min Act: 0.0001

Data Index: 1540751 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4773. Min Act: 0.0002

Data Index: 1554601 (Python Code)

Max Activating Token Index: 471

Text #7

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1415103 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4258. Min Act: 0.0002

Data Index: 1494697 (Python Code)

Max Activating Token Index: 296

Text #9

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4230. Min Act: 0.0002

Data Index: 1600302 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4306. Min Act: 0.0001

Data Index: 1485414 (Python Code)

Max Activating Token Index: 463

Text #11

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4169. Min Act: 0.0002

Data Index: 1460709 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4380. Min Act: 0.0002

Data Index: 1572836 (Python Code)

Max Activating Token Index: 589

Text #13

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4269. Min Act: 0.0001

Data Index: 1605385 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4290. Min Act: -0.0000

Data Index: 1475751 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.4074. Min Act: 0.0002

Data Index: 1411309 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.3646. Min Act: 0.0002

Data Index: 1627653 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.3854. Min Act: -0.0000

Data Index: 1384131 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1587996 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.5481. Min Range: -0.5481

Max Act: 0.3763. Min Act: -0.0001

Data Index: 1529643 (Python Code)

Max Activating Token Index: 108