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

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

Neuron 4378 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: 2.0188. Min Range: -2.0188

Max Act: 2.0188. Min Act: -0.0000

Data Index: 1119996 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.9092. Min Act: -0.0000

Data Index: 798799 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.7286. Min Act: -0.0000

Data Index: 620240 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.5507. Min Act: -0.0000

Data Index: 27246 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.3330. Min Act: -0.0000

Data Index: 977776 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1121792 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.2242. Min Act: -0.0000

Data Index: 782152 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1338758 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1246. Min Act: -0.0000

Data Index: 1190891 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1215667 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1803. Min Act: -0.0000

Data Index: 328774 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1178219 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1852. Min Act: -0.0000

Data Index: 731502 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1330. Min Act: -0.0000

Data Index: 343885 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1514230 (Python Code)

Max Activating Token Index: 607

Text #15

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1777. Min Act: -0.0000

Data Index: 497814 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1415681 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1563085 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 2.0188. Min Range: -2.0188

Max Act: 1.0777. Min Act: -0.0000

Data Index: 957400 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 2.0188. Min Range: -2.0188

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1029100 (C4 (Web Text))

Max Activating Token Index: 683