Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3973 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.6316. Min Act: -0.0001

Data Index: 747887 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5993. Min Act: -0.0000

Data Index: 845475 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1146188 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5722. Min Act: -0.0000

Data Index: 977996 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.6091. Min Act: -0.0000

Data Index: 926149 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1151218 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5257. Min Act: -0.0000

Data Index: 493045 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5091. Min Act: -0.0000

Data Index: 993193 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4941. Min Act: -0.0000

Data Index: 441534 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4923. Min Act: -0.0000

Data Index: 916322 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4671. Min Act: -0.0000

Data Index: 492752 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.5146. Min Act: -0.0001

Data Index: 452783 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4566. Min Act: -0.0000

Data Index: 490 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4617. Min Act: -0.0000

Data Index: 299876 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4428. Min Act: -0.0000

Data Index: 425974 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4432. Min Act: -0.0001

Data Index: 697069 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1252987 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4239. Min Act: -0.0001

Data Index: 726239 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4490. Min Act: -0.0000

Data Index: 319284 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.6316. Min Range: -0.6316

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1223280 (C4 (Web Text))

Max Activating Token Index: 665