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

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

Neuron 5187 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5701. Min Range: -1.5701

Max Act: 1.5701. Min Act: -0.0000

Data Index: 24769 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 1.5701. Min Range: -1.5701

Max Act: 1.3721. Min Act: 0.0000

Data Index: 478280 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.5701. Min Range: -1.5701

Max Act: 1.0412. Min Act: -0.0000

Data Index: 799253 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.9563. Min Act: -0.0000

Data Index: 510596 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1261908 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8027. Min Act: 0.0000

Data Index: 1293789 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8563. Min Act: -0.0000

Data Index: 332027 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1045410 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.7860. Min Act: 0.0000

Data Index: 554071 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1314970 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8300. Min Act: 0.0000

Data Index: 785116 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1214127 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.7715. Min Act: -0.0000

Data Index: 480735 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.7807. Min Act: -0.0000

Data Index: 216380 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.6654. Min Act: -0.0000

Data Index: 289469 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.7660. Min Act: 0.0000

Data Index: 90205 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8032. Min Act: -0.0000

Data Index: 905665 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1211159 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1170116 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.5701. Min Range: -1.5701

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1170099 (C4 (Web Text))

Max Activating Token Index: 681