Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5019 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1382309 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1259558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1204. Min Act: -0.0000

Data Index: 247512 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1232. Min Act: -0.0000

Data Index: 567026 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1207702 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1186. Min Act: -0.0000

Data Index: 767611 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1142. Min Act: -0.0000

Data Index: 334526 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1606835 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1043. Min Act: -0.0000

Data Index: 342293 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1282863 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1510491 (Python Code)

Max Activating Token Index: 813

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1301448 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0950. Min Act: -0.0000

Data Index: 308041 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0971. Min Act: -0.0000

Data Index: 516293 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1363068 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1194226 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0961. Min Act: -0.0000

Data Index: 675878 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0952. Min Act: -0.0000

Data Index: 922255 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1417498 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.0913. Min Act: -0.0000

Data Index: 425859 (C4 (Web Text))

Max Activating Token Index: 344