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

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

Neuron 339 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6334. Min Range: -2.6334

Max Act: 2.6334. Min Act: -0.0000

Data Index: 1506434 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1615538 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.6123. Min Act: -0.0000

Data Index: 1649894 (Python Code)

Max Activating Token Index: 648

Text #3

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1601565 (Python Code)

Max Activating Token Index: 929

Text #4

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1638602 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1594665 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.4314. Min Act: -0.0000

Data Index: 1636832 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1652603 (Python Code)

Max Activating Token Index: 552

Text #8

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2892. Min Act: -0.0000

Data Index: 1576819 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1599671 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.3073. Min Act: -0.0000

Data Index: 1569815 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1380572 (Python Code)

Max Activating Token Index: 549

Text #12

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1644497 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1486405 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2178. Min Act: -0.0000

Data Index: 1467257 (Python Code)

Max Activating Token Index: 562

Text #15

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.1899. Min Act: -0.0000

Data Index: 1426320 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1463404 (Python Code)

Max Activating Token Index: 899

Text #17

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1544340 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1637598 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 2.6334. Min Range: -2.6334

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1599710 (Python Code)

Max Activating Token Index: 326