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

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

Neuron 4383 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4583. Min Act: -0.0000

Data Index: 978585 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4414. Min Act: -0.0000

Data Index: 282396 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3737. Min Act: -0.0000

Data Index: 875966 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3353. Min Act: -0.0000

Data Index: 526754 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2352. Min Act: -0.0000

Data Index: 483184 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2437. Min Act: -0.0000

Data Index: 882448 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2054. Min Act: -0.0000

Data Index: 482009 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1996. Min Act: -0.0000

Data Index: 748451 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1289. Min Act: -0.0000

Data Index: 729008 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0992. Min Act: -0.0000

Data Index: 438605 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0283. Min Act: -0.0000

Data Index: 384687 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0125. Min Act: -0.0000

Data Index: 478906 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0741. Min Act: -0.0000

Data Index: 114953 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0046. Min Act: -0.0000

Data Index: 838287 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1291147 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1296835 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0561. Min Act: -0.0000

Data Index: 1280329 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1228039 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0531. Min Act: -0.0000

Data Index: 829521 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0114. Min Act: -0.0000

Data Index: 471734 (C4 (Web Text))

Max Activating Token Index: 27