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

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

Neuron 50 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1247436 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.7402. Min Act: -0.0000

Data Index: 305395 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1350785 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1175613 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5646. Min Act: -0.0000

Data Index: 238828 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5411. Min Act: -0.0000

Data Index: 612678 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5068. Min Act: -0.0000

Data Index: 933627 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.5041. Min Act: -0.0000

Data Index: 46113 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1322112 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4612. Min Act: -0.0000

Data Index: 262631 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4605. Min Act: -0.0000

Data Index: 796197 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1110480 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4909. Min Act: -0.0000

Data Index: 74582 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4772. Min Act: -0.0000

Data Index: 480421 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4721. Min Act: -0.0000

Data Index: 740179 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4704. Min Act: -0.0000

Data Index: 690675 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4498. Min Act: -0.0000

Data Index: 472586 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4667. Min Act: -0.0000

Data Index: 525891 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1226855 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 0.7510. Min Range: -0.7510

Max Act: 0.4150. Min Act: -0.0000

Data Index: 828588 (C4 (Web Text))

Max Activating Token Index: 238