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

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

Neuron 3815 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: 0.0136. Min Range: -0.0136

Max Act: 0.0134. Min Act: -0.0002

Data Index: 602448 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0002

Data Index: 641658 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0126. Min Act: -0.0003

Data Index: 213638 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0002

Data Index: 329766 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0123. Min Act: -0.0002

Data Index: 190363 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1337433 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0118. Min Act: -0.0002

Data Index: 135175 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0002

Data Index: 925228 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0002

Data Index: 871497 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0002

Data Index: 371869 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0113. Min Act: -0.0002

Data Index: 325440 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0002

Data Index: 459517 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0002

Data Index: 382081 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0002

Data Index: 415971 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0002

Data Index: 1299514 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0107. Min Act: -0.0002

Data Index: 964773 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0002

Data Index: 237698 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0002

Data Index: 882481 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0002

Data Index: 260081 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0002

Data Index: 606858 (C4 (Web Text))

Max Activating Token Index: 522