Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 849 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.4369. Min Act: -0.0005

Data Index: 380085 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.4754. Min Act: -0.0005

Data Index: 26307 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3937. Min Act: -0.0005

Data Index: 262745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3910. Min Act: -0.0005

Data Index: 1205385 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3881. Min Act: -0.0005

Data Index: 1023786 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3424. Min Act: -0.0005

Data Index: 1071791 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3890. Min Act: -0.0005

Data Index: 920508 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3748. Min Act: -0.0005

Data Index: 287666 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3883. Min Act: -0.0005

Data Index: 218956 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3548. Min Act: -0.0005

Data Index: 953854 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3770. Min Act: -0.0005

Data Index: 1305401 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3638. Min Act: -0.0005

Data Index: 279240 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3834. Min Act: -0.0005

Data Index: 946702 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3804. Min Act: -0.0005

Data Index: 196901 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3531. Min Act: -0.0005

Data Index: 708710 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3637. Min Act: -0.0005

Data Index: 245816 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3636. Min Act: -0.0005

Data Index: 49826 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3484. Min Act: -0.0005

Data Index: 264972 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3480. Min Act: -0.0005

Data Index: 124824 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.4754. Min Range: -0.4754

Max Act: 0.3603. Min Act: -0.0005

Data Index: 364004 (C4 (Web Text))

Max Activating Token Index: 510