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

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

Neuron 2745 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: 2.1110. Min Range: -2.1110

Max Act: 2.1110. Min Act: -0.0000

Data Index: 947267 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1452126 (Python Code)

Max Activating Token Index: 745

Text #2

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.9596. Min Act: -0.0000

Data Index: 1622248 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.8183. Min Act: -0.0000

Data Index: 1461190 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1375773 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1401620 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1409327 (Python Code)

Max Activating Token Index: 285

Text #7

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1364209 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1509034 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1641647 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1484099 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.8676. Min Act: -0.0000

Data Index: 1645001 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.6380. Min Act: -0.0000

Data Index: 332128 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1392708 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1641416 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4799. Min Act: -0.0000

Data Index: 1421544 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.7578. Min Act: -0.0000

Data Index: 1501407 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1548550 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.5488. Min Act: -0.0000

Data Index: 719659 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 2.1110. Min Range: -2.1110

Max Act: 1.4575. Min Act: -0.0000

Data Index: 1403990 (Python Code)

Max Activating Token Index: 369