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

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

Neuron 4093 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: 0.4298. Min Range: -0.4298

Max Act: 0.4085. Min Act: -0.0002

Data Index: 306642 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4186. Min Act: -0.0001

Data Index: 1205270 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3763. Min Act: -0.0001

Data Index: 967372 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4298. Min Act: -0.0001

Data Index: 1330023 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3814. Min Act: -0.0002

Data Index: 585460 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3813. Min Act: -0.0002

Data Index: 1259498 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3885. Min Act: -0.0001

Data Index: 693511 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3880. Min Act: -0.0002

Data Index: 1127776 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3795. Min Act: -0.0002

Data Index: 923154 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3481. Min Act: -0.0002

Data Index: 1258082 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3926. Min Act: -0.0002

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3823. Min Act: -0.0002

Data Index: 285913 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3770. Min Act: -0.0002

Data Index: 179032 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3466. Min Act: -0.0002

Data Index: 1040039 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3635. Min Act: -0.0001

Data Index: 180453 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3848. Min Act: -0.0002

Data Index: 23644 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3345. Min Act: -0.0001

Data Index: 556057 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3822. Min Act: -0.0002

Data Index: 153620 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.3589. Min Act: -0.0002

Data Index: 358165 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.4298. Min Range: -0.4298

Max Act: 0.4061. Min Act: -0.0001

Data Index: 419236 (C4 (Web Text))

Max Activating Token Index: 703