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

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

Neuron 3024 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: 0.6758. Min Range: -0.6758

Max Act: 0.6758. Min Act: -0.0000

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5123. Min Act: -0.0000

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5663. Min Act: -0.0000

Data Index: 967099 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5324. Min Act: -0.0000

Data Index: 455288 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.4756. Min Act: -0.0000

Data Index: 715785 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5675. Min Act: -0.0000

Data Index: 382726 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5380. Min Act: -0.0000

Data Index: 12678 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5407. Min Act: -0.0000

Data Index: 274408 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5460. Min Act: -0.0000

Data Index: 674234 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5594. Min Act: -0.0000

Data Index: 997064 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5180. Min Act: -0.0000

Data Index: 170697 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.4971. Min Act: -0.0000

Data Index: 1028204 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5290. Min Act: -0.0000

Data Index: 330979 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5010. Min Act: -0.0000

Data Index: 52172 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5167. Min Act: -0.0000

Data Index: 649431 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5203. Min Act: -0.0000

Data Index: 731191 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5229. Min Act: -0.0000

Data Index: 244830 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1085507 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.5193. Min Act: -0.0000

Data Index: 485021 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.6758. Min Range: -0.6758

Max Act: 0.4635. Min Act: -0.0000

Data Index: 282388 (C4 (Web Text))

Max Activating Token Index: 47