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

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

Neuron 674 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.4622. Min Act: -0.0000

Data Index: 351372 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.2515. Min Act: -0.0001

Data Index: 1063441 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1944. Min Act: -0.0000

Data Index: 1179514 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1750. Min Act: -0.0001

Data Index: 916410 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.2401. Min Act: -0.0001

Data Index: 15894 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1319. Min Act: -0.0000

Data Index: 290362 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1741. Min Act: -0.0000

Data Index: 282003 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.2734. Min Act: -0.0000

Data Index: 947960 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0234. Min Act: -0.0001

Data Index: 195666 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0337. Min Act: -0.0000

Data Index: 600743 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1208. Min Act: -0.0000

Data Index: 556628 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 2.4622. Min Range: -2.4622

Max Act: 1.9925. Min Act: -0.0001

Data Index: 431658 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0864. Min Act: -0.0000

Data Index: 443680 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0754. Min Act: -0.0000

Data Index: 157589 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0265. Min Act: -0.0001

Data Index: 1285903 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0230. Min Act: -0.0000

Data Index: 707078 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.4622. Min Range: -2.4622

Max Act: 1.9182. Min Act: -0.0000

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.1098. Min Act: -0.0001

Data Index: 112007 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 2.4622. Min Range: -2.4622

Max Act: 2.0073. Min Act: -0.0000

Data Index: 724847 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 2.4622. Min Range: -2.4622

Max Act: 1.7714. Min Act: -0.0001

Data Index: 1177980 (C4 (Web Text))

Max Activating Token Index: 558