Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3154 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0912. Min Range: -1.0912

Max Act: 1.0912. Min Act: -0.0001

Data Index: 1243286 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.9436. Min Act: -0.0001

Data Index: 785998 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.8736. Min Act: -0.0001

Data Index: 358750 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1113081 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.8322. Min Act: -0.0001

Data Index: 47771 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.7905. Min Act: -0.0001

Data Index: 337948 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.7614. Min Act: -0.0001

Data Index: 218073 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1265350 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6790. Min Act: -0.0001

Data Index: 693708 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1186239 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6747. Min Act: -0.0001

Data Index: 1014095 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6728. Min Act: -0.0001

Data Index: 885345 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1257081 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1331533 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6359. Min Act: -0.0001

Data Index: 167499 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6613. Min Act: -0.0001

Data Index: 1146236 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.5859. Min Act: -0.0001

Data Index: 662424 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6095. Min Act: -0.0000

Data Index: 223162 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.5966. Min Act: -0.0001

Data Index: 655226 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.0912. Min Range: -1.0912

Max Act: 0.6208. Min Act: -0.0001

Data Index: 176042 (C4 (Web Text))

Max Activating Token Index: 962