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

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

Neuron 5485 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.4234. Min Act: -0.0000

Data Index: 263899 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1550701 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1451935 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.2942. Min Act: -0.0000

Data Index: 275438 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.3157. Min Act: 0.0000

Data Index: 1619546 (Python Code)

Max Activating Token Index: 342

Text #5

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.3052. Min Act: 0.0000

Data Index: 1501173 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.2664. Min Act: 0.0000

Data Index: 1477236 (Python Code)

Max Activating Token Index: 217

Text #7

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.1848. Min Act: -0.0000

Data Index: 1460045 (Python Code)

Max Activating Token Index: 978

Text #8

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.1576. Min Act: 0.0000

Data Index: 1622856 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1475874 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.2319. Min Act: -0.0000

Data Index: 1604742 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1537139 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0000. Min Act: 0.0000

Data Index: 1546217 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0121. Min Act: -0.0000

Data Index: 358194 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0134. Min Act: -0.0000

Data Index: 11304 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0016. Min Act: 0.0001

Data Index: 1399861 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 1.5602. Min Range: -1.5602

Max Act: 0.9925. Min Act: -0.0000

Data Index: 4912 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1505456 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 1.5602. Min Range: -1.5602

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1580966 (Python Code)

Max Activating Token Index: 492

Text #19

Max Range: 1.5602. Min Range: -1.5602

Max Act: 1.0045. Min Act: 0.0000

Data Index: 1382416 (Python Code)

Max Activating Token Index: 826