Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 524 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1125103 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0199. Min Act: -0.0006

Data Index: 282652 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0189. Min Act: -0.0006

Data Index: 589697 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0193. Min Act: -0.0006

Data Index: 994003 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1225904 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1105458 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0192. Min Act: -0.0006

Data Index: 703723 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1284031 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0183. Min Act: -0.0006

Data Index: 926715 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0184. Min Act: -0.0006

Data Index: 564251 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1409154 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1500088 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1573483 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0180. Min Act: -0.0006

Data Index: 361651 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0184. Min Act: -0.0006

Data Index: 1165396 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1155123 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0178. Min Act: -0.0006

Data Index: 518271 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1066122 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0177. Min Act: -0.0006

Data Index: 999780 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.0199. Min Range: -0.0199

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1201372 (C4 (Web Text))

Max Activating Token Index: 824