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

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

Neuron 1659 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: 1.0126. Min Range: -1.0126

Max Act: 1.0126. Min Act: -0.0000

Data Index: 322390 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8748. Min Act: 0.0000

Data Index: 230194 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.8241. Min Act: -0.0000

Data Index: 551931 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7481. Min Act: 0.0000

Data Index: 575909 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.7399. Min Act: 0.0000

Data Index: 929699 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6272. Min Act: -0.0000

Data Index: 25980 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1118359 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6619. Min Act: -0.0000

Data Index: 680304 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6144. Min Act: -0.0000

Data Index: 724612 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6109. Min Act: -0.0000

Data Index: 702370 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6422. Min Act: -0.0000

Data Index: 627419 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.5958. Min Act: -0.0000

Data Index: 549109 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6083. Min Act: -0.0000

Data Index: 442461 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6239. Min Act: -0.0000

Data Index: 87231 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6210. Min Act: 0.0000

Data Index: 402214 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.6401. Min Act: -0.0000

Data Index: 497267 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.5949. Min Act: 0.0000

Data Index: 807256 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.5673. Min Act: -0.0000

Data Index: 702873 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.5833. Min Act: 0.0000

Data Index: 652390 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.0126. Min Range: -1.0126

Max Act: 0.5641. Min Act: 0.0000

Data Index: 705153 (C4 (Web Text))

Max Activating Token Index: 614