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

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

Neuron 3184 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: 0.3796. Min Range: -0.3796

Max Act: 0.3796. Min Act: -0.0000

Data Index: 662321 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3192. Min Act: -0.0000

Data Index: 895605 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3490. Min Act: -0.0000

Data Index: 825383 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.3212. Min Act: -0.0000

Data Index: 290325 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2647. Min Act: -0.0001

Data Index: 410054 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2145. Min Act: -0.0000

Data Index: 1061491 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2427. Min Act: -0.0000

Data Index: 775639 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1323093 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2322. Min Act: -0.0000

Data Index: 960413 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2400. Min Act: -0.0000

Data Index: 1556078 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2401. Min Act: -0.0000

Data Index: 892725 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1258086 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2106. Min Act: -0.0000

Data Index: 840180 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2128. Min Act: -0.0000

Data Index: 731495 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2065. Min Act: -0.0000

Data Index: 47250 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2094. Min Act: -0.0000

Data Index: 909807 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1113747 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.1678. Min Act: -0.0000

Data Index: 881159 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.3796. Min Range: -0.3796

Max Act: 0.2035. Min Act: -0.0000

Data Index: 408738 (C4 (Web Text))

Max Activating Token Index: 306