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

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

Neuron 701 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0403. Min Range: -2.0403

Max Act: 2.0403. Min Act: -0.0000

Data Index: 1292667 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 2.0403. Min Range: -2.0403

Max Act: 2.0005. Min Act: -0.0000

Data Index: 154495 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.9282. Min Act: -0.0000

Data Index: 602855 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1415872 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.8215. Min Act: -0.0000

Data Index: 689850 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.8154. Min Act: -0.0000

Data Index: 1586337 (Python Code)

Max Activating Token Index: 250

Text #6

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1169036 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.9548. Min Act: -0.0000

Data Index: 1036914 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.7110. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.5234. Min Act: -0.0000

Data Index: 1606788 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.7008. Min Act: -0.0000

Data Index: 466991 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6963. Min Act: -0.0000

Data Index: 346914 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6703. Min Act: -0.0000

Data Index: 1329057 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6304. Min Act: -0.0000

Data Index: 746173 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6190. Min Act: -0.0000

Data Index: 1187035 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6272. Min Act: -0.0000

Data Index: 382177 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.5216. Min Act: -0.0000

Data Index: 1225944 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1283852 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.7701. Min Act: -0.0000

Data Index: 57193 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 2.0403. Min Range: -2.0403

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1366972 (Python Code)

Max Activating Token Index: 355