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

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

Neuron 4848 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.4664. Min Act: -0.0001

Data Index: 1204212 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.4559. Min Act: -0.0001

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3774. Min Act: -0.0000

Data Index: 676432 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3737. Min Act: -0.0001

Data Index: 944004 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3625. Min Act: -0.0001

Data Index: 822853 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.4389. Min Act: -0.0001

Data Index: 51848 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3964. Min Act: -0.0001

Data Index: 834122 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2201. Min Act: -0.0001

Data Index: 169934 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3380. Min Act: -0.0001

Data Index: 1064359 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2788. Min Act: -0.0000

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3017. Min Act: -0.0001

Data Index: 380335 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3024. Min Act: -0.0001

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.1566. Min Act: -0.0000

Data Index: 1238164 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3596. Min Act: -0.0000

Data Index: 329906 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2345. Min Act: -0.0001

Data Index: 1080652 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2289. Min Act: -0.0001

Data Index: 649220 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2092. Min Act: -0.0001

Data Index: 423344 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2055. Min Act: -0.0001

Data Index: 721919 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2060. Min Act: -0.0001

Data Index: 187175 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2250. Min Act: -0.0001

Data Index: 674166 (C4 (Web Text))

Max Activating Token Index: 459