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

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

Neuron 2559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.2694. Min Act: -0.0000

Data Index: 983816 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1212935 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.0419. Min Act: -0.0001

Data Index: 437027 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9328. Min Act: -0.0000

Data Index: 59898 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7979. Min Act: -0.0001

Data Index: 854362 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8057. Min Act: -0.0001

Data Index: 359144 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7866. Min Act: -0.0000

Data Index: 580019 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7766. Min Act: -0.0000

Data Index: 855149 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1262741 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1197940 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1222568 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7182. Min Act: -0.0001

Data Index: 943893 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1225259 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7059. Min Act: -0.0000

Data Index: 392140 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6747. Min Act: -0.0001

Data Index: 233254 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6751. Min Act: -0.0001

Data Index: 266393 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1080343 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6837. Min Act: -0.0001

Data Index: 185563 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6378. Min Act: -0.0001

Data Index: 378228 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.6221. Min Act: -0.0001

Data Index: 59778 (C4 (Web Text))

Max Activating Token Index: 888