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

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

Neuron 3428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5525. Min Act: -0.0000

Data Index: 956842 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6299. Min Act: -0.0000

Data Index: 317692 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5201. Min Act: -0.0001

Data Index: 742579 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2597. Min Act: -0.0001

Data Index: 855427 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3671. Min Act: -0.0001

Data Index: 708006 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3018. Min Act: -0.0000

Data Index: 1180154 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6004. Min Act: -0.0001

Data Index: 1007198 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2339. Min Act: -0.0000

Data Index: 738485 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1136623 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2177. Min Act: -0.0001

Data Index: 483124 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.0572. Min Act: -0.0000

Data Index: 333272 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3154. Min Act: -0.0001

Data Index: 618150 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2857. Min Act: -0.0000

Data Index: 908983 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2020. Min Act: -0.0000

Data Index: 246562 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.1184. Min Act: -0.0001

Data Index: 602419 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1283578 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.2005. Min Act: -0.0001

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.1281. Min Act: -0.0001

Data Index: 732990 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.1108. Min Act: -0.0001

Data Index: 1072806 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.0839. Min Act: -0.0001

Data Index: 278027 (C4 (Web Text))

Max Activating Token Index: 560