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

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

Neuron 37 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1254857 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1645. Min Act: -0.0000

Data Index: 687914 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1554. Min Act: -0.0000

Data Index: 483288 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1495. Min Act: -0.0001

Data Index: 872380 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1167017 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1450. Min Act: -0.0001

Data Index: 922766 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1292. Min Act: -0.0000

Data Index: 151788 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1369. Min Act: -0.0000

Data Index: 484560 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1576754 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1362. Min Act: -0.0000

Data Index: 676579 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1174788 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1292. Min Act: -0.0000

Data Index: 198762 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1270. Min Act: -0.0000

Data Index: 281806 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1221. Min Act: -0.0000

Data Index: 330811 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1258. Min Act: -0.0000

Data Index: 41591 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1247. Min Act: -0.0000

Data Index: 332734 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1486059 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1196. Min Act: -0.0000

Data Index: 907604 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1149. Min Act: -0.0000

Data Index: 638905 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1228. Min Act: -0.0000

Data Index: 1175946 (C4 (Web Text))

Max Activating Token Index: 484