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

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

Neuron 1554 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: 1.3560. Min Range: -1.3560

Max Act: 1.3560. Min Act: -0.0002

Data Index: 411462 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.1680. Min Act: -0.0002

Data Index: 174617 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.0727. Min Act: -0.0002

Data Index: 522510 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.0969. Min Act: -0.0002

Data Index: 1003199 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.0402. Min Act: -0.0002

Data Index: 1260321 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.0215. Min Act: -0.0002

Data Index: 511179 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.0122. Min Act: -0.0002

Data Index: 609803 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9554. Min Act: -0.0002

Data Index: 1105369 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9458. Min Act: -0.0002

Data Index: 331045 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9153. Min Act: -0.0002

Data Index: 408284 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8612. Min Act: -0.0002

Data Index: 611906 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8099. Min Act: -0.0002

Data Index: 704752 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8519. Min Act: -0.0002

Data Index: 582982 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8458. Min Act: -0.0002

Data Index: 59309 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8211. Min Act: -0.0002

Data Index: 375862 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8651. Min Act: -0.0002

Data Index: 376594 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8420. Min Act: -0.0002

Data Index: 1019032 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8292. Min Act: -0.0002

Data Index: 430115 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8305. Min Act: -0.0002

Data Index: 926646 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8281. Min Act: -0.0002

Data Index: 465687 (C4 (Web Text))

Max Activating Token Index: 94