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

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

Neuron 3282 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: 0.2839. Min Range: -0.2839

Max Act: 0.2839. Min Act: -0.0002

Data Index: 1012198 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2660. Min Act: -0.0002

Data Index: 425298 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2564. Min Act: -0.0002

Data Index: 313490 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2566. Min Act: -0.0002

Data Index: 60107 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2534. Min Act: -0.0002

Data Index: 892198 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2475. Min Act: -0.0002

Data Index: 921297 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2483. Min Act: -0.0003

Data Index: 401323 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2480. Min Act: -0.0002

Data Index: 371661 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2352. Min Act: -0.0003

Data Index: 77732 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2387. Min Act: -0.0002

Data Index: 544831 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2349. Min Act: -0.0002

Data Index: 1344423 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2324. Min Act: -0.0002

Data Index: 344387 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2300. Min Act: -0.0002

Data Index: 12808 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2281. Min Act: -0.0002

Data Index: 607601 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2267. Min Act: -0.0002

Data Index: 50261 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2223. Min Act: -0.0002

Data Index: 1246376 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2260. Min Act: -0.0003

Data Index: 1356239 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2224. Min Act: -0.0003

Data Index: 776599 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2240. Min Act: -0.0003

Data Index: 805132 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2261. Min Act: -0.0003

Data Index: 339078 (C4 (Web Text))

Max Activating Token Index: 223