Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 277 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3960. Min Range: -3.3960

Max Act: 3.3730. Min Act: -0.0000

Data Index: 1514043 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 3.3960. Min Range: -3.3960

Max Act: 3.3960. Min Act: -0.0000

Data Index: 919529 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.8149. Min Act: -0.0000

Data Index: 1461271 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.3998. Min Act: -0.0000

Data Index: 1523608 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.6058. Min Act: -0.0000

Data Index: 45938 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.6211. Min Act: -0.0000

Data Index: 615365 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.3769. Min Act: -0.0000

Data Index: 446417 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.1528. Min Act: -0.0000

Data Index: 1526208 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.4136. Min Act: -0.0000

Data Index: 1599330 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.2905. Min Act: -0.0000

Data Index: 1372470 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.4738. Min Act: -0.0000

Data Index: 1420619 (Python Code)

Max Activating Token Index: 926

Text #11

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.1121. Min Act: -0.0000

Data Index: 1441950 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.3393. Min Act: -0.0000

Data Index: 1433388 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.2834. Min Act: -0.0000

Data Index: 1623228 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.3112. Min Act: -0.0000

Data Index: 57600 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.1646. Min Act: -0.0000

Data Index: 1434131 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 3.3960. Min Range: -3.3960

Max Act: 2.0619. Min Act: -0.0000

Data Index: 791022 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.3960. Min Range: -3.3960

Max Act: 1.8489. Min Act: -0.0000

Data Index: 41389 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 3.3960. Min Range: -3.3960

Max Act: 1.9470. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.3960. Min Range: -3.3960

Max Act: 1.9988. Min Act: -0.0000

Data Index: 46093 (C4 (Web Text))

Max Activating Token Index: 835