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

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

Neuron 753 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.9322. Min Act: -0.0001

Data Index: 117664 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.0143. Min Range: -1.0143

Max Act: 1.0143. Min Act: -0.0001

Data Index: 389615 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7857. Min Act: -0.0001

Data Index: 47771 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7909. Min Act: -0.0001

Data Index: 575301 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7049. Min Act: -0.0001

Data Index: 285482 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6911. Min Act: -0.0001

Data Index: 1181853 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6631. Min Act: -0.0001

Data Index: 755829 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6969. Min Act: -0.0001

Data Index: 998115 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.7077. Min Act: -0.0001

Data Index: 857413 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6793. Min Act: -0.0001

Data Index: 1177943 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6718. Min Act: -0.0001

Data Index: 439399 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6639. Min Act: -0.0001

Data Index: 948197 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6695. Min Act: -0.0000

Data Index: 870059 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6162. Min Act: -0.0001

Data Index: 687462 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6296. Min Act: -0.0001

Data Index: 180821 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6053. Min Act: -0.0001

Data Index: 1014323 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.6320. Min Act: -0.0001

Data Index: 239822 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1079382 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5590. Min Act: -0.0001

Data Index: 707195 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 1.0143. Min Range: -1.0143

Max Act: 0.5172. Min Act: -0.0001

Data Index: 362442 (C4 (Web Text))

Max Activating Token Index: 775