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

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

Neuron 1750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 753068 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1268965 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0533. Min Act: -0.0002

Data Index: 490123 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1548277 (Python Code)

Max Activating Token Index: 1007

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0588. Min Act: -0.0002

Data Index: 433684 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0575. Min Act: -0.0002

Data Index: 354401 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0654. Min Act: -0.0002

Data Index: 84355 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0571. Min Act: -0.0002

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0549. Min Act: -0.0002

Data Index: 993529 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0557. Min Act: -0.0002

Data Index: 901302 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0538. Min Act: -0.0002

Data Index: 715341 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0572. Min Act: -0.0002

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0586. Min Act: -0.0002

Data Index: 665420 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0593. Min Act: -0.0001

Data Index: 930871 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0523. Min Act: -0.0001

Data Index: 649133 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1359652 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0555. Min Act: -0.0001

Data Index: 108998 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0544. Min Act: -0.0001

Data Index: 1490762 (Python Code)

Max Activating Token Index: 417

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1299401 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1595750 (Python Code)

Max Activating Token Index: 619