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

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

Neuron 625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2914. Min Act: -0.0000

Data Index: 599630 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2343. Min Act: -0.0000

Data Index: 676930 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2494. Min Act: -0.0000

Data Index: 728067 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2670. Min Act: -0.0000

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2273. Min Act: -0.0000

Data Index: 578403 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2536. Min Act: -0.0000

Data Index: 995986 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2271. Min Act: -0.0000

Data Index: 134800 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1849. Min Act: -0.0000

Data Index: 446280 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2137. Min Act: -0.0000

Data Index: 130218 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1844. Min Act: -0.0000

Data Index: 303445 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2054. Min Act: -0.0000

Data Index: 413658 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1001285 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2070. Min Act: -0.0000

Data Index: 511783 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1355814 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1996. Min Act: -0.0000

Data Index: 141316 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1867. Min Act: -0.0000

Data Index: 277728 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.2031. Min Act: -0.0000

Data Index: 506923 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1951. Min Act: -0.0000

Data Index: 812685 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1278891 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.2914. Min Range: -0.2914

Max Act: 0.1611. Min Act: -0.0000

Data Index: 830503 (C4 (Web Text))

Max Activating Token Index: 278