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

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

Neuron 1998 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2367. Min Act: -0.0000

Data Index: 235422 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1266462 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2525. Min Act: -0.0000

Data Index: 120924 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2478. Min Act: -0.0000

Data Index: 135062 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2547. Min Act: -0.0000

Data Index: 47738 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2418. Min Act: -0.0000

Data Index: 873103 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1170567 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2239. Min Act: -0.0000

Data Index: 884264 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2059. Min Act: -0.0000

Data Index: 121083 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1328919 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2199. Min Act: -0.0000

Data Index: 146823 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2239. Min Act: -0.0000

Data Index: 510736 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1037415 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2297. Min Act: -0.0000

Data Index: 798607 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2191. Min Act: -0.0000

Data Index: 78952 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2011. Min Act: -0.0000

Data Index: 413893 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2005. Min Act: -0.0000

Data Index: 572670 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1174801 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1855. Min Act: -0.0000

Data Index: 631270 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.2547. Min Range: -0.2547

Max Act: 0.1980. Min Act: -0.0000

Data Index: 406216 (C4 (Web Text))

Max Activating Token Index: 216