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

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

Neuron 3947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1353329 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1120388 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1227213 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6760. Min Act: -0.0000

Data Index: 107446 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5400. Min Act: -0.0000

Data Index: 176407 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6530. Min Act: -0.0000

Data Index: 656050 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5851. Min Act: -0.0000

Data Index: 524834 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7112. Min Act: -0.0000

Data Index: 726283 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6236. Min Act: -0.0000

Data Index: 14247 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6183. Min Act: -0.0000

Data Index: 912267 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6070. Min Act: -0.0000

Data Index: 551074 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6256. Min Act: -0.0000

Data Index: 162306 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5824. Min Act: -0.0000

Data Index: 255153 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6148. Min Act: -0.0000

Data Index: 601490 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1302346 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1016847 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5556. Min Act: -0.0000

Data Index: 712403 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5961. Min Act: -0.0000

Data Index: 892748 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5872. Min Act: -0.0000

Data Index: 265338 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6048. Min Act: -0.0000

Data Index: 987445 (C4 (Web Text))

Max Activating Token Index: 1000