Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0001

Data Index: 150919 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7937. Min Act: -0.0001

Data Index: 3753 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6979. Min Act: -0.0001

Data Index: 536310 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6971. Min Act: -0.0001

Data Index: 696491 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6485. Min Act: -0.0001

Data Index: 859812 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7421. Min Act: -0.0001

Data Index: 653772 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6382. Min Act: -0.0001

Data Index: 222806 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1207688 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6315. Min Act: -0.0001

Data Index: 1191903 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6443. Min Act: -0.0001

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1212502 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6329. Min Act: -0.0001

Data Index: 771943 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6035. Min Act: -0.0000

Data Index: 676312 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5949. Min Act: -0.0000

Data Index: 715157 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1341072 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5812. Min Act: -0.0001

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5581. Min Act: -0.0001

Data Index: 452413 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1304279 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5728. Min Act: -0.0001

Data Index: 1253003 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.5560. Min Act: -0.0000

Data Index: 515740 (C4 (Web Text))

Max Activating Token Index: 568