Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4049 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0136. Min Act: -0.0002

Data Index: 68662 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0166. Min Act: -0.0002

Data Index: 303235 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0002

Data Index: 703159 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1166648 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0166. Min Act: -0.0002

Data Index: 216496 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1313410 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0173. Min Act: -0.0002

Data Index: 766484 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0163. Min Act: -0.0002

Data Index: 762790 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0157. Min Act: -0.0002

Data Index: 809037 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 655485 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0171. Min Act: -0.0002

Data Index: 742191 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1275885 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0159. Min Act: -0.0002

Data Index: 134257 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1328945 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0119. Min Act: -0.0002

Data Index: 534363 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0138. Min Act: -0.0002

Data Index: 787086 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1267961 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0147. Min Act: -0.0002

Data Index: 284797 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0123. Min Act: -0.0002

Data Index: 111743 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1328544 (C4 (Web Text))

Max Activating Token Index: 929