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

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

Neuron 1059 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: 0.8096. Min Range: -0.8096

Max Act: 0.8096. Min Act: -0.0002

Data Index: 1531843 (Python Code)

Max Activating Token Index: 262

Text #1

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6037. Min Act: -0.0002

Data Index: 1548710 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5697. Min Act: -0.0002

Data Index: 1214475 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5436. Min Act: -0.0002

Data Index: 1513485 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5413. Min Act: -0.0002

Data Index: 1046335 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5406. Min Act: -0.0002

Data Index: 29702 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5156. Min Act: -0.0002

Data Index: 32599 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5227. Min Act: -0.0002

Data Index: 1596561 (Python Code)

Max Activating Token Index: 173

Text #8

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5263. Min Act: -0.0002

Data Index: 502085 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5219. Min Act: -0.0002

Data Index: 911470 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5194. Min Act: -0.0002

Data Index: 957066 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5065. Min Act: -0.0002

Data Index: 24388 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4935. Min Act: -0.0002

Data Index: 822763 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4973. Min Act: -0.0002

Data Index: 634036 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4917. Min Act: -0.0002

Data Index: 1384285 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4959. Min Act: -0.0002

Data Index: 1255260 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4995. Min Act: -0.0002

Data Index: 1304749 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4993. Min Act: -0.0002

Data Index: 941605 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4919. Min Act: -0.0002

Data Index: 1618823 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4926. Min Act: -0.0002

Data Index: 923564 (C4 (Web Text))

Max Activating Token Index: 385