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

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

Neuron 1526 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: 0.4773. Min Range: -0.4773

Max Act: 0.4773. Min Act: -0.0001

Data Index: 471005 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4418. Min Act: -0.0002

Data Index: 633275 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4481. Min Act: -0.0001

Data Index: 790921 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4250. Min Act: -0.0001

Data Index: 1049608 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3989. Min Act: -0.0002

Data Index: 635340 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3984. Min Act: -0.0002

Data Index: 489558 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4273. Min Act: -0.0002

Data Index: 929234 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3906. Min Act: -0.0002

Data Index: 1344878 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3994. Min Act: -0.0001

Data Index: 91159 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3942. Min Act: -0.0001

Data Index: 371082 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1281888 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.4063. Min Act: -0.0002

Data Index: 229578 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3990. Min Act: -0.0001

Data Index: 991497 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3968. Min Act: -0.0001

Data Index: 817097 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3851. Min Act: -0.0001

Data Index: 1275155 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3770. Min Act: -0.0001

Data Index: 906171 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3777. Min Act: -0.0002

Data Index: 533214 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3704. Min Act: -0.0002

Data Index: 872638 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.4773. Min Range: -0.4773

Max Act: 0.3878. Min Act: -0.0002

Data Index: 736633 (C4 (Web Text))

Max Activating Token Index: 583