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

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

Neuron 3853 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1463084 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1597715 (Python Code)

Max Activating Token Index: 403

Text #2

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1607921 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1441712 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1528943 (Python Code)

Max Activating Token Index: 366

Text #5

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1562242 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1257410 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1570988 (Python Code)

Max Activating Token Index: 579

Text #8

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1470453 (Python Code)

Max Activating Token Index: 184

Text #9

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4538. Min Act: 0.0000

Data Index: 959158 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4528. Min Act: 0.0000

Data Index: 1196492 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1484158 (Python Code)

Max Activating Token Index: 934

Text #12

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1650984 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1497365 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4172. Min Act: 0.0000

Data Index: 565849 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4116. Min Act: -0.0000

Data Index: 679893 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1404146 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1482064 (Python Code)

Max Activating Token Index: 175

Text #18

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.3437. Min Act: -0.0000

Data Index: 1485796 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.8999. Min Range: -0.8999

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1428099 (Python Code)

Max Activating Token Index: 626