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

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

Neuron 1682 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7207. Min Range: -4.7207

Max Act: 4.7207. Min Act: -0.0000

Data Index: 474401 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.8434. Min Act: -0.0000

Data Index: 378266 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.4765. Min Act: -0.0000

Data Index: 194918 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.4737. Min Act: -0.0000

Data Index: 754047 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.6115. Min Act: -0.0000

Data Index: 1191051 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1045. Min Act: -0.0000

Data Index: 645341 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.3385. Min Act: -0.0000

Data Index: 568686 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.3808. Min Act: -0.0000

Data Index: 826134 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.3331. Min Act: -0.0000

Data Index: 1168038 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 4.7207. Min Range: -4.7207

Max Act: 2.9979. Min Act: -0.0000

Data Index: 973656 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1278. Min Act: -0.0000

Data Index: 39626 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1397. Min Act: -0.0000

Data Index: 856794 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1175. Min Act: -0.0000

Data Index: 165223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1006. Min Act: -0.0000

Data Index: 120064 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.0838. Min Act: -0.0000

Data Index: 937171 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.0860. Min Act: -0.0000

Data Index: 489829 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 4.7207. Min Range: -4.7207

Max Act: 2.7790. Min Act: -0.0000

Data Index: 1352130 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 4.7207. Min Range: -4.7207

Max Act: 3.1252. Min Act: -0.0000

Data Index: 105632 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 4.7207. Min Range: -4.7207

Max Act: 2.8930. Min Act: -0.0000

Data Index: 784444 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 4.7207. Min Range: -4.7207

Max Act: 2.8847. Min Act: -0.0000

Data Index: 1229459 (C4 (Web Text))

Max Activating Token Index: 450