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

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

Neuron 3564 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: 0.0201. Min Range: -0.0201

Max Act: 0.0201. Min Act: -0.0002

Data Index: 980806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1304787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0180. Min Act: -0.0002

Data Index: 90479 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0177. Min Act: -0.0002

Data Index: 450972 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1271939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1578935 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0167. Min Act: -0.0002

Data Index: 429921 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0167. Min Act: -0.0002

Data Index: 796499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0161. Min Act: -0.0002

Data Index: 173626 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0160. Min Act: -0.0002

Data Index: 909655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0159. Min Act: -0.0003

Data Index: 748408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0158. Min Act: -0.0002

Data Index: 237425 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0157. Min Act: -0.0002

Data Index: 280763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0154. Min Act: -0.0002

Data Index: 849237 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1472690 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1478296 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0153. Min Act: -0.0002

Data Index: 967661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0148. Min Act: -0.0002

Data Index: 32898 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0201. Min Range: -0.0201

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1148552 (C4 (Web Text))

Max Activating Token Index: 1023