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

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

Neuron 384 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: 0.0211. Min Range: -0.0211

Max Act: 0.0211. Min Act: -0.0002

Data Index: 5879 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0162. Min Act: -0.0003

Data Index: 670191 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0161. Min Act: -0.0002

Data Index: 159403 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0159. Min Act: -0.0002

Data Index: 304357 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0156. Min Act: -0.0003

Data Index: 183405 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1197544 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0150. Min Act: -0.0002

Data Index: 796564 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0150. Min Act: -0.0002

Data Index: 179935 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0150. Min Act: -0.0003

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0147. Min Act: -0.0002

Data Index: 636514 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0148. Min Act: -0.0002

Data Index: 391405 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0146. Min Act: -0.0002

Data Index: 70673 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1542990 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0148. Min Act: -0.0002

Data Index: 919730 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1257390 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0144. Min Act: -0.0002

Data Index: 64912 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0138. Min Act: -0.0002

Data Index: 57868 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1179219 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0132. Min Act: -0.0002

Data Index: 548445 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.0211. Min Range: -0.0211

Max Act: 0.0132. Min Act: -0.0002

Data Index: 241325 (C4 (Web Text))

Max Activating Token Index: 25