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

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

Neuron 3475 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1974. Min Act: -0.0001

Data Index: 530613 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1335154 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2383. Min Act: -0.0001

Data Index: 391852 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2345. Min Act: -0.0001

Data Index: 881987 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1130948 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1039862 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1989. Min Act: -0.0001

Data Index: 803479 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2061. Min Act: -0.0001

Data Index: 577650 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1884. Min Act: -0.0001

Data Index: 824062 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1610. Min Act: -0.0001

Data Index: 164501 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1625. Min Act: -0.0001

Data Index: 430212 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1603. Min Act: -0.0001

Data Index: 563070 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1542. Min Act: -0.0001

Data Index: 740771 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1321867 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1698. Min Act: -0.0001

Data Index: 230332 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1249165 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1565. Min Act: -0.0001

Data Index: 569097 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1109887 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1422. Min Act: -0.0001

Data Index: 692610 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1404. Min Act: -0.0001

Data Index: 862327 (C4 (Web Text))

Max Activating Token Index: 853