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

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

Neuron 5878 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: 0.3143. Min Range: -0.3143

Max Act: 0.3143. Min Act: -0.0002

Data Index: 604284 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2661. Min Act: -0.0002

Data Index: 134947 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2378. Min Act: -0.0002

Data Index: 249991 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2331. Min Act: -0.0002

Data Index: 225478 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2307. Min Act: -0.0002

Data Index: 362487 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2272. Min Act: -0.0002

Data Index: 681374 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2194. Min Act: -0.0003

Data Index: 599964 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2245. Min Act: -0.0002

Data Index: 901649 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2180. Min Act: -0.0002

Data Index: 1022784 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2177. Min Act: -0.0002

Data Index: 1177016 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2137. Min Act: -0.0002

Data Index: 491339 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2098. Min Act: -0.0002

Data Index: 1331566 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2130. Min Act: -0.0002

Data Index: 961876 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2087. Min Act: -0.0002

Data Index: 911589 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2091. Min Act: -0.0002

Data Index: 778049 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2112. Min Act: -0.0002

Data Index: 959987 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2079. Min Act: -0.0002

Data Index: 890391 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2051. Min Act: -0.0002

Data Index: 591151 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2054. Min Act: -0.0002

Data Index: 1092343 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.3143. Min Range: -0.3143

Max Act: 0.2076. Min Act: -0.0002

Data Index: 838595 (C4 (Web Text))

Max Activating Token Index: 660