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

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

Neuron 3259 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: 0.4449. Min Range: -0.4449

Max Act: 0.4449. Min Act: -0.0002

Data Index: 1579240 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4438. Min Act: -0.0002

Data Index: 324038 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4314. Min Act: -0.0002

Data Index: 1534363 (Python Code)

Max Activating Token Index: 747

Text #3

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4339. Min Act: -0.0002

Data Index: 1637238 (Python Code)

Max Activating Token Index: 650

Text #4

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4302. Min Act: -0.0002

Data Index: 135398 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4242. Min Act: -0.0002

Data Index: 827591 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4235. Min Act: -0.0002

Data Index: 546788 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4296. Min Act: -0.0003

Data Index: 406731 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4150. Min Act: -0.0002

Data Index: 307271 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4191. Min Act: -0.0002

Data Index: 749883 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4114. Min Act: -0.0002

Data Index: 1346792 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4202. Min Act: -0.0002

Data Index: 1625770 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4102. Min Act: -0.0002

Data Index: 1325883 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4199. Min Act: -0.0002

Data Index: 260075 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4082. Min Act: -0.0002

Data Index: 1326638 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4120. Min Act: -0.0002

Data Index: 1560061 (Python Code)

Max Activating Token Index: 786

Text #16

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4204. Min Act: -0.0002

Data Index: 1532003 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4097. Min Act: -0.0002

Data Index: 755080 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4066. Min Act: -0.0002

Data Index: 315120 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.4449. Min Range: -0.4449

Max Act: 0.4142. Min Act: -0.0002

Data Index: 139947 (C4 (Web Text))

Max Activating Token Index: 111