Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3785. Min Act: -0.0001

Data Index: 554991 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2709. Min Act: -0.0000

Data Index: 153395 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2385. Min Act: -0.0000

Data Index: 943209 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2291. Min Act: -0.0000

Data Index: 503786 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1566. Min Act: -0.0001

Data Index: 355203 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1552. Min Act: -0.0000

Data Index: 209687 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1122964 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1185314 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1045410 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1158. Min Act: -0.0000

Data Index: 766715 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1062. Min Act: -0.0000

Data Index: 269489 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1122. Min Act: -0.0001

Data Index: 599237 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1097. Min Act: -0.0000

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1291212 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0830. Min Act: -0.0000

Data Index: 682316 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1240182 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0929. Min Act: -0.0000

Data Index: 695766 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0975. Min Act: -0.0001

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.1008. Min Act: -0.0000

Data Index: 34580 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.0762. Min Act: -0.0000

Data Index: 329663 (C4 (Web Text))

Max Activating Token Index: 79