Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5406 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.3421. Min Act: -0.0000

Data Index: 793431 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1313511 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2555. Min Act: 0.0000

Data Index: 613037 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2673. Min Act: -0.0000

Data Index: 564410 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2423. Min Act: -0.0000

Data Index: 555575 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2426. Min Act: -0.0000

Data Index: 326828 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1248108 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1202465 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2216. Min Act: -0.0000

Data Index: 889448 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2354. Min Act: -0.0000

Data Index: 954169 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2193. Min Act: -0.0000

Data Index: 477947 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2333. Min Act: -0.0000

Data Index: 210847 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2140. Min Act: -0.0000

Data Index: 571065 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2074. Min Act: -0.0000

Data Index: 989128 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2019. Min Act: -0.0000

Data Index: 406594 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2029. Min Act: -0.0000

Data Index: 663559 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.1985. Min Act: -0.0000

Data Index: 94200 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.2115. Min Act: -0.0000

Data Index: 208743 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.1919. Min Act: 0.0000

Data Index: 1134311 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.3421. Min Range: -0.3421

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1107224 (C4 (Web Text))

Max Activating Token Index: 824