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

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

Neuron 1280 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: 0.8048. Min Range: -0.8048

Max Act: 0.8048. Min Act: 0.0000

Data Index: 1205466 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5850. Min Act: -0.0000

Data Index: 561071 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1314882 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5488. Min Act: 0.0001

Data Index: 764924 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1123695 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5296. Min Act: -0.0000

Data Index: 276797 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4924. Min Act: -0.0000

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5117. Min Act: 0.0000

Data Index: 1239105 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.5161. Min Act: -0.0000

Data Index: 498097 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4576. Min Act: -0.0000

Data Index: 548868 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4448. Min Act: -0.0000

Data Index: 321141 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4416. Min Act: 0.0000

Data Index: 641580 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4000. Min Act: -0.0000

Data Index: 132750 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4373. Min Act: -0.0000

Data Index: 75195 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4185. Min Act: 0.0000

Data Index: 1309997 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.3866. Min Act: -0.0000

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4011. Min Act: 0.0000

Data Index: 1214257 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.4164. Min Act: -0.0000

Data Index: 592267 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.8048. Min Range: -0.8048

Max Act: 0.3782. Min Act: 0.0000

Data Index: 834326 (C4 (Web Text))

Max Activating Token Index: 256