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

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

Neuron 165 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: 0.2333. Min Range: -0.2333

Max Act: 0.2329. Min Act: -0.0003

Data Index: 1114289 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2333. Min Act: -0.0002

Data Index: 1151536 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2331. Min Act: -0.0002

Data Index: 1301369 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2223. Min Act: -0.0002

Data Index: 1058332 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2211. Min Act: -0.0003

Data Index: 387388 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2237. Min Act: -0.0002

Data Index: 636183 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2171. Min Act: -0.0003

Data Index: 483260 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2126. Min Act: -0.0002

Data Index: 610879 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2122. Min Act: -0.0003

Data Index: 1108997 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2135. Min Act: -0.0002

Data Index: 645369 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1052398 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2101. Min Act: -0.0003

Data Index: 537527 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2118. Min Act: -0.0002

Data Index: 1265685 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2059. Min Act: -0.0002

Data Index: 1235856 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2058. Min Act: -0.0003

Data Index: 436710 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2061. Min Act: -0.0002

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2062. Min Act: -0.0002

Data Index: 185110 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2009. Min Act: -0.0002

Data Index: 1054723 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.2036. Min Act: -0.0002

Data Index: 889073 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.2333. Min Range: -0.2333

Max Act: 0.1981. Min Act: -0.0003

Data Index: 173659 (C4 (Web Text))

Max Activating Token Index: 976