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

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

Neuron 2146 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0283. Min Range: -6.0283

Max Act: 6.0283. Min Act: -0.0000

Data Index: 650136 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 6.0283. Min Range: -6.0283

Max Act: 5.1570. Min Act: -0.0000

Data Index: 582935 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 6.0283. Min Range: -6.0283

Max Act: 4.9416. Min Act: -0.0000

Data Index: 964152 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 6.0283. Min Range: -6.0283

Max Act: 3.0562. Min Act: -0.0000

Data Index: 1059934 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.9937. Min Act: -0.0000

Data Index: 765376 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.7214. Min Act: -0.0000

Data Index: 403083 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6830. Min Act: -0.0000

Data Index: 427842 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6557. Min Act: -0.0000

Data Index: 328149 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6511. Min Act: -0.0000

Data Index: 806267 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.7243. Min Act: -0.0000

Data Index: 982740 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.7139. Min Act: -0.0000

Data Index: 983465 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.4406. Min Act: -0.0000

Data Index: 602880 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6212. Min Act: -0.0000

Data Index: 740082 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.7353. Min Act: -0.0000

Data Index: 824366 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.5632. Min Act: -0.0000

Data Index: 69554 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6545. Min Act: -0.0000

Data Index: 1049080 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.5289. Min Act: -0.0000

Data Index: 46709 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.4807. Min Act: -0.0000

Data Index: 6009 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.6163. Min Act: -0.0000

Data Index: 844600 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 6.0283. Min Range: -6.0283

Max Act: 2.2838. Min Act: -0.0000

Data Index: 309837 (C4 (Web Text))

Max Activating Token Index: 918