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

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

Neuron 1641 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.1040. Min Act: -0.0001

Data Index: 91703 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 1.1040. Min Range: -1.1040

Max Act: 1.0605. Min Act: -0.0001

Data Index: 1114067 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9664. Min Act: -0.0001

Data Index: 396770 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.9397. Min Act: -0.0001

Data Index: 744616 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8917. Min Act: -0.0001

Data Index: 622660 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7637. Min Act: -0.0001

Data Index: 199477 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8797. Min Act: -0.0001

Data Index: 1148008 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7272. Min Act: -0.0001

Data Index: 86996 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8221. Min Act: -0.0001

Data Index: 478192 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7871. Min Act: -0.0001

Data Index: 91804 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8842. Min Act: -0.0001

Data Index: 412429 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8399. Min Act: -0.0001

Data Index: 819642 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7908. Min Act: -0.0001

Data Index: 706379 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7605. Min Act: -0.0001

Data Index: 367733 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7135. Min Act: -0.0001

Data Index: 871341 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1332689 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.8007. Min Act: -0.0001

Data Index: 589407 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7354. Min Act: -0.0001

Data Index: 23931 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7783. Min Act: -0.0001

Data Index: 1114354 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.1040. Min Range: -1.1040

Max Act: 0.7434. Min Act: -0.0001

Data Index: 763865 (C4 (Web Text))

Max Activating Token Index: 949