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

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

Neuron 386 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7313. Min Range: -4.7313

Max Act: 4.7313. Min Act: -0.0000

Data Index: 1217 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.9491. Min Act: -0.0000

Data Index: 411358 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 4.7313. Min Range: -4.7313

Max Act: 4.0471. Min Act: -0.0000

Data Index: 354045 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.7701. Min Act: -0.0000

Data Index: 814187 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.7642. Min Act: -0.0000

Data Index: 718650 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.5200. Min Act: -0.0000

Data Index: 1288190 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.4348. Min Act: -0.0000

Data Index: 12955 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.4308. Min Act: -0.0000

Data Index: 277978 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.1632. Min Act: -0.0000

Data Index: 177673 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2744. Min Act: -0.0000

Data Index: 310636 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2643. Min Act: -0.0000

Data Index: 973998 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 4.7313. Min Range: -4.7313

Max Act: 2.9442. Min Act: -0.0000

Data Index: 1144560 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2186. Min Act: -0.0000

Data Index: 1113685 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2050. Min Act: -0.0000

Data Index: 371374 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.3435. Min Act: -0.0000

Data Index: 1355617 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.1791. Min Act: -0.0000

Data Index: 1194664 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.1495. Min Act: -0.0000

Data Index: 836646 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2674. Min Act: -0.0000

Data Index: 514373 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.1185. Min Act: -0.0000

Data Index: 1059772 (C4 (Web Text))

Max Activating Token Index: 102

Text #19

Max Range: 4.7313. Min Range: -4.7313

Max Act: 3.2841. Min Act: -0.0000

Data Index: 1219968 (C4 (Web Text))

Max Activating Token Index: 893