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

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

Neuron 50 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: 0.5138. Min Range: -0.5138

Max Act: 0.5119. Min Act: -0.0001

Data Index: 276701 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.5138. Min Act: -0.0001

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4637. Min Act: -0.0001

Data Index: 58410 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4896. Min Act: -0.0001

Data Index: 891578 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4629. Min Act: -0.0001

Data Index: 283496 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4378. Min Act: -0.0001

Data Index: 839134 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.4102. Min Act: -0.0001

Data Index: 1188768 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3620. Min Act: -0.0001

Data Index: 819896 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3763. Min Act: -0.0001

Data Index: 493369 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3622. Min Act: -0.0001

Data Index: 1300460 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3581. Min Act: -0.0001

Data Index: 1148294 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3507. Min Act: -0.0001

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3562. Min Act: -0.0001

Data Index: 816151 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3547. Min Act: -0.0001

Data Index: 981215 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3530. Min Act: -0.0001

Data Index: 1191462 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3380. Min Act: -0.0001

Data Index: 529383 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3404. Min Act: -0.0001

Data Index: 282194 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1163718 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3463. Min Act: -0.0001

Data Index: 1170242 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.5138. Min Range: -0.5138

Max Act: 0.3398. Min Act: -0.0001

Data Index: 612384 (C4 (Web Text))

Max Activating Token Index: 947