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

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

Neuron 4497 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: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0002

Data Index: 551008 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0130. Min Act: -0.0002

Data Index: 543525 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0126. Min Act: -0.0002

Data Index: 957819 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1394403 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1205574 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1393034 (Python Code)

Max Activating Token Index: 1012

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0110. Min Act: -0.0001

Data Index: 1558305 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1427466 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1388439 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1270478 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0105. Min Act: -0.0002

Data Index: 476764 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1013221 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1575232 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1373542 (Python Code)

Max Activating Token Index: 1017

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0101. Min Act: -0.0002

Data Index: 226308 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1508944 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0098. Min Act: -0.0002

Data Index: 407217 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1422595 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1409504 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0096. Min Act: -0.0002

Data Index: 1413252 (Python Code)

Max Activating Token Index: 1001