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

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

Neuron 1991 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: 0.0194. Min Range: -0.0194

Max Act: 0.0194. Min Act: -0.0002

Data Index: 801338 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1492363 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1474117 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0166. Min Act: -0.0002

Data Index: 617082 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0161. Min Act: -0.0002

Data Index: 139780 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0162. Min Act: -0.0002

Data Index: 759732 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1641615 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1508551 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1231590 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0154. Min Act: -0.0002

Data Index: 361283 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1040416 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0149. Min Act: -0.0002

Data Index: 752 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1428244 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0142. Min Act: -0.0002

Data Index: 17940 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0143. Min Act: -0.0002

Data Index: 99705 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0143. Min Act: -0.0002

Data Index: 358867 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1406056 (Python Code)

Max Activating Token Index: 997

Text #17

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1551725 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1360944 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 0.0194. Min Range: -0.0194

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1541760 (Python Code)

Max Activating Token Index: 1021