Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 301 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1328832 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.9221. Min Act: -0.0000

Data Index: 188505 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.9417. Min Act: -0.0000

Data Index: 779540 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.9401. Min Act: -0.0000

Data Index: 767741 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.9279. Min Act: -0.0000

Data Index: 576895 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.8595. Min Act: -0.0000

Data Index: 532930 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.8488. Min Act: -0.0000

Data Index: 584031 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.7800. Min Act: -0.0000

Data Index: 1223827 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.8070. Min Act: -0.0000

Data Index: 1135182 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6922. Min Act: -0.0000

Data Index: 474059 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.7634. Min Act: -0.0000

Data Index: 562806 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1515333 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.7240. Min Act: -0.0000

Data Index: 662927 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1479755 (Python Code)

Max Activating Token Index: 266

Text #14

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1276430 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1232894 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1359720 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6257. Min Act: -0.0000

Data Index: 544217 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1531289 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 1.9417. Min Range: -1.9417

Max Act: 1.6727. Min Act: -0.0000

Data Index: 538997 (C4 (Web Text))

Max Activating Token Index: 549