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

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

Neuron 1810 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.9995. Min Act: -0.0000

Data Index: 1325981 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.7827. Min Act: -0.0000

Data Index: 127000 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.5937. Min Act: -0.0001

Data Index: 408602 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.5251. Min Act: -0.0000

Data Index: 970754 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.5216. Min Act: -0.0000

Data Index: 943380 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4970. Min Act: -0.0000

Data Index: 728556 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4622. Min Act: -0.0000

Data Index: 457632 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4540. Min Act: -0.0000

Data Index: 658018 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4060. Min Act: -0.0000

Data Index: 90325 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1311256 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3722. Min Act: -0.0000

Data Index: 23333 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3603. Min Act: -0.0000

Data Index: 717744 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3943. Min Act: -0.0000

Data Index: 681647 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3973. Min Act: -0.0000

Data Index: 825880 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3967. Min Act: -0.0000

Data Index: 126331 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4201. Min Act: -0.0000

Data Index: 489005 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3770. Min Act: -0.0001

Data Index: 115550 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1347915 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4183. Min Act: -0.0001

Data Index: 670069 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.9995. Min Range: -1.9995

Max Act: 1.4224. Min Act: -0.0000

Data Index: 774558 (C4 (Web Text))

Max Activating Token Index: 702