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

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

Neuron 151 in Layer 0

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: 0.2285. Min Range: -0.2285

Max Act: 0.2285. Min Act: -0.0001

Data Index: 327759 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2251. Min Act: -0.0001

Data Index: 973684 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2222. Min Act: -0.0001

Data Index: 917773 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2201. Min Act: -0.0001

Data Index: 13826 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2203. Min Act: -0.0001

Data Index: 312923 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1169549 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1286495 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2190. Min Act: -0.0001

Data Index: 448365 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2113. Min Act: -0.0001

Data Index: 313977 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2170. Min Act: -0.0001

Data Index: 101219 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2116. Min Act: -0.0001

Data Index: 847696 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1040075 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2152. Min Act: -0.0001

Data Index: 760237 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2104. Min Act: -0.0001

Data Index: 70310 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2161. Min Act: -0.0001

Data Index: 576621 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1281930 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2171. Min Act: -0.0001

Data Index: 497712 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1047852 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1323013 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2100. Min Act: -0.0001

Data Index: 818401 (C4 (Web Text))

Max Activating Token Index: 22