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

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

Neuron 4572 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0425. Min Act: -0.0002

Data Index: 174614 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0002

Data Index: 555863 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0401. Min Act: -0.0002

Data Index: 865474 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1060723 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1197672 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0363. Min Act: -0.0002

Data Index: 681792 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1024394 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0350. Min Act: -0.0002

Data Index: 64327 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1541216 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0347. Min Act: -0.0002

Data Index: 729249 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1142347 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0325. Min Act: -0.0002

Data Index: 505266 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1277663 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1253057 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1463371 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0328. Min Act: -0.0002

Data Index: 559304 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0317. Min Act: -0.0002

Data Index: 429321 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0318. Min Act: -0.0002

Data Index: 978203 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0307. Min Act: -0.0002

Data Index: 599439 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0312. Min Act: -0.0002

Data Index: 898641 (C4 (Web Text))

Max Activating Token Index: 911