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

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

Neuron 4935 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: 3.1583. Min Range: -3.1583

Max Act: 2.7793. Min Act: -0.0000

Data Index: 88135 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.1583. Min Range: -3.1583

Max Act: 3.0817. Min Act: -0.0000

Data Index: 536278 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8586. Min Act: -0.0000

Data Index: 168107 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 3.1583. Min Range: -3.1583

Max Act: 3.1583. Min Act: -0.0000

Data Index: 319375 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.9649. Min Act: -0.0000

Data Index: 1272379 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1176592 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.1583. Min Range: -3.1583

Max Act: 3.0487. Min Act: -0.0000

Data Index: 1153609 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.9049. Min Act: -0.0000

Data Index: 1327915 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 3.1583. Min Range: -3.1583

Max Act: 3.0578. Min Act: -0.0000

Data Index: 895151 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 3.1583. Min Range: -3.1583

Max Act: 3.0434. Min Act: -0.0000

Data Index: 854452 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8823. Min Act: -0.0000

Data Index: 1320765 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8611. Min Act: -0.0000

Data Index: 1095480 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8451. Min Act: -0.0000

Data Index: 1304227 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8319. Min Act: -0.0000

Data Index: 967671 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8176. Min Act: -0.0000

Data Index: 908131 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8034. Min Act: -0.0000

Data Index: 322649 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.7631. Min Act: -0.0000

Data Index: 223774 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.7797. Min Act: -0.0000

Data Index: 1316668 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.6250. Min Act: -0.0000

Data Index: 916294 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.1583. Min Range: -3.1583

Max Act: 2.8944. Min Act: -0.0000

Data Index: 600047 (C4 (Web Text))

Max Activating Token Index: 244