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

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

Neuron 4077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.5779. Min Act: -0.0000

Data Index: 321953 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1169867 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.5979. Min Act: 0.0000

Data Index: 352627 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.5191. Min Act: -0.0000

Data Index: 90229 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4978. Min Act: -0.0000

Data Index: 394755 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1123377 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1300594 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1242310 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4850. Min Act: -0.0000

Data Index: 407128 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1217985 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4566. Min Act: -0.0000

Data Index: 149647 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1348304 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4273. Min Act: 0.0000

Data Index: 575332 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4393. Min Act: -0.0000

Data Index: 623141 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4671. Min Act: -0.0000

Data Index: 817721 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1296869 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1035672 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4576. Min Act: -0.0000

Data Index: 443718 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4216. Min Act: 0.0000

Data Index: 996861 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.5979. Min Range: -0.5979

Max Act: 0.4241. Min Act: -0.0000

Data Index: 574119 (C4 (Web Text))

Max Activating Token Index: 58