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

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

Neuron 3804 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1342973 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1358558 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1440901 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1204101 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1490347 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1442094 (Python Code)

Max Activating Token Index: 214

Text #7

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1566272 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1628766 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1370480 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1497021 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1546185 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1630213 (Python Code)

Max Activating Token Index: 58

Text #13

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1570590 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1590668 (Python Code)

Max Activating Token Index: 809

Text #15

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0244. Min Act: -0.0002

Data Index: 565459 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0243. Min Act: -0.0002

Data Index: 483972 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0241. Min Act: -0.0002

Data Index: 995113 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0247. Min Act: -0.0002

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0293. Min Range: -0.0293

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1566096 (Python Code)

Max Activating Token Index: 77