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

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

Neuron 5028 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: 0.5177. Min Range: -0.5177

Max Act: 0.5177. Min Act: -0.0002

Data Index: 61227 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.5166. Min Act: -0.0002

Data Index: 542049 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4949. Min Act: -0.0002

Data Index: 628049 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4757. Min Act: -0.0002

Data Index: 617721 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4669. Min Act: -0.0002

Data Index: 136741 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4726. Min Act: -0.0002

Data Index: 568034 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4656. Min Act: -0.0002

Data Index: 39691 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4575. Min Act: -0.0002

Data Index: 328245 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4533. Min Act: -0.0002

Data Index: 1273261 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4520. Min Act: -0.0002

Data Index: 22198 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4420. Min Act: -0.0002

Data Index: 53870 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4389. Min Act: -0.0002

Data Index: 170643 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4387. Min Act: -0.0002

Data Index: 828229 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4427. Min Act: -0.0002

Data Index: 226728 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4293. Min Act: -0.0002

Data Index: 368989 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4343. Min Act: -0.0002

Data Index: 649888 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4255. Min Act: -0.0002

Data Index: 526363 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4325. Min Act: -0.0002

Data Index: 664938 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4267. Min Act: -0.0002

Data Index: 1276826 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.5177. Min Range: -0.5177

Max Act: 0.4221. Min Act: -0.0002

Data Index: 54450 (C4 (Web Text))

Max Activating Token Index: 283