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

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

Neuron 2435 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.9323. Min Act: -0.0000

Data Index: 433955 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.9709. Min Act: -0.0000

Data Index: 398322 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8640. Min Act: -0.0000

Data Index: 80266 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8561. Min Act: -0.0000

Data Index: 588213 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1055561 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1328481 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1242655 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7995. Min Act: -0.0000

Data Index: 536785 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8443. Min Act: -0.0000

Data Index: 538283 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8242. Min Act: -0.0000

Data Index: 133825 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1351889 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7656. Min Act: -0.0000

Data Index: 970888 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7261. Min Act: -0.0000

Data Index: 342163 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8338. Min Act: -0.0000

Data Index: 954231 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.8171. Min Act: -0.0000

Data Index: 150166 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7873. Min Act: -0.0000

Data Index: 820325 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7829. Min Act: -0.0000

Data Index: 952731 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7808. Min Act: -0.0000

Data Index: 348038 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7697. Min Act: -0.0000

Data Index: 604410 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.9709. Min Range: -0.9709

Max Act: 0.7685. Min Act: -0.0000

Data Index: 449382 (C4 (Web Text))

Max Activating Token Index: 111