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

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

Neuron 3465 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6871. Min Act: -0.0000

Data Index: 766293 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6430. Min Act: -0.0000

Data Index: 490040 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1259253 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6161. Min Act: -0.0000

Data Index: 722625 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.6281. Min Act: -0.0000

Data Index: 345362 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5631. Min Act: -0.0000

Data Index: 364007 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5310. Min Act: -0.0000

Data Index: 713876 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1204782 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5265. Min Act: -0.0000

Data Index: 598308 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1112061 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5402. Min Act: -0.0000

Data Index: 204890 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5576. Min Act: -0.0000

Data Index: 959214 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4998. Min Act: -0.0000

Data Index: 626795 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1000315 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5027. Min Act: -0.0000

Data Index: 191397 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5116. Min Act: -0.0000

Data Index: 191219 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1296430 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5112. Min Act: -0.0000

Data Index: 348234 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5337. Min Act: -0.0000

Data Index: 877821 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.6871. Min Range: -0.6871

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1347437 (C4 (Web Text))

Max Activating Token Index: 741