Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.1011. Min Act: -0.0001

Data Index: 762677 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0843. Min Act: -0.0001

Data Index: 402229 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0910. Min Act: -0.0001

Data Index: 660162 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1206480 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0812. Min Act: -0.0001

Data Index: 66829 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0802. Min Act: -0.0001

Data Index: 173886 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0801. Min Act: -0.0001

Data Index: 889779 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0755. Min Act: -0.0001

Data Index: 261050 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1575608 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0757. Min Act: -0.0001

Data Index: 1472294 (Python Code)

Max Activating Token Index: 432

Text #10

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0746. Min Act: -0.0001

Data Index: 307802 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0740. Min Act: -0.0001

Data Index: 821592 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0740. Min Act: -0.0001

Data Index: 570498 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0691. Min Act: -0.0001

Data Index: 426654 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0681. Min Act: -0.0001

Data Index: 27290 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1338289 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0751. Min Act: -0.0001

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0788. Min Act: -0.0001

Data Index: 44030 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1276447 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.1011. Min Range: -0.1011

Max Act: 0.0695. Min Act: -0.0001

Data Index: 351150 (C4 (Web Text))

Max Activating Token Index: 770