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

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

Neuron 3099 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: 1.2368. Min Range: -1.2368

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1358089 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1015363 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.2182. Min Act: -0.0000

Data Index: 672501 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1313. Min Act: -0.0000

Data Index: 888165 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1245. Min Act: -0.0000

Data Index: 325081 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1094453 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1272689 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1410. Min Act: -0.0000

Data Index: 842113 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0736. Min Act: -0.0000

Data Index: 272468 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1226153 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0619. Min Act: -0.0000

Data Index: 669622 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0346. Min Act: -0.0000

Data Index: 577640 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1946. Min Act: -0.0000

Data Index: 1075542 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0891. Min Act: -0.0000

Data Index: 370655 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0967. Min Act: -0.0000

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1094664 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1096082 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.1168. Min Act: -0.0000

Data Index: 686207 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0756. Min Act: -0.0000

Data Index: 440897 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 1.2368. Min Range: -1.2368

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1008241 (C4 (Web Text))

Max Activating Token Index: 338