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

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

Neuron 4521 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: 1.8945. Min Range: -1.8945

Max Act: 1.8945. Min Act: -0.0000

Data Index: 270567 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.3591. Min Act: -0.0000

Data Index: 851673 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.2924. Min Act: -0.0000

Data Index: 310509 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.3060. Min Act: -0.0000

Data Index: 615719 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1308436 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1035208 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1871. Min Act: -0.0000

Data Index: 99246 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1178648 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0833. Min Act: -0.0000

Data Index: 514565 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1178453 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1020081 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9895. Min Act: -0.0000

Data Index: 194733 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0023. Min Act: -0.0000

Data Index: 1248143 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.8945. Min Range: -1.8945

Max Act: 1.0213. Min Act: -0.0000

Data Index: 1064430 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9007. Min Act: -0.0000

Data Index: 673404 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1113239 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9560. Min Act: -0.0000

Data Index: 963945 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1266044 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1340982 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.8945. Min Range: -1.8945

Max Act: 0.8572. Min Act: -0.0000

Data Index: 335867 (C4 (Web Text))

Max Activating Token Index: 959