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

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

Neuron 3840 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.1543. Min Act: -0.0001

Data Index: 1491231 (Python Code)

Max Activating Token Index: 345

Text #1

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.3377. Min Act: -0.0001

Data Index: 1501032 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.1149. Min Act: -0.0001

Data Index: 1391863 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.0953. Min Act: -0.0001

Data Index: 1582976 (Python Code)

Max Activating Token Index: 406

Text #4

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.9297. Min Act: -0.0001

Data Index: 1557789 (Python Code)

Max Activating Token Index: 385

Text #5

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.7967. Min Act: -0.0001

Data Index: 1592485 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8978. Min Act: -0.0001

Data Index: 1410056 (Python Code)

Max Activating Token Index: 223

Text #7

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.1478. Min Act: -0.0001

Data Index: 1538497 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8714. Min Act: -0.0001

Data Index: 1380020 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 3.3377. Min Range: -3.3377

Max Act: 3.0818. Min Act: -0.0001

Data Index: 1488267 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8870. Min Act: -0.0001

Data Index: 1403018 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.9035. Min Act: -0.0001

Data Index: 1647872 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8979. Min Act: -0.0001

Data Index: 1596611 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.7531. Min Act: -0.0001

Data Index: 1603023 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8812. Min Act: -0.0001

Data Index: 1426347 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8913. Min Act: -0.0001

Data Index: 1631350 (Python Code)

Max Activating Token Index: 366

Text #16

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.7476. Min Act: -0.0001

Data Index: 1362090 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8895. Min Act: -0.0001

Data Index: 1500043 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.8822. Min Act: -0.0001

Data Index: 1494066 (Python Code)

Max Activating Token Index: 359

Text #19

Max Range: 3.3377. Min Range: -3.3377

Max Act: 2.6935. Min Act: -0.0001

Data Index: 1509865 (Python Code)

Max Activating Token Index: 100