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

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

Neuron 363 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1651. Min Act: -0.0001

Data Index: 510950 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1169580 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1218. Min Act: -0.0001

Data Index: 689873 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1041. Min Act: -0.0001

Data Index: 856162 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1092. Min Act: -0.0001

Data Index: 291699 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1066. Min Act: -0.0001

Data Index: 795356 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1022. Min Act: -0.0001

Data Index: 101911 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1054. Min Act: -0.0001

Data Index: 325223 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1011. Min Act: -0.0001

Data Index: 557101 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1019. Min Act: -0.0001

Data Index: 530022 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1007. Min Act: -0.0001

Data Index: 665284 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1417157 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0957. Min Act: -0.0001

Data Index: 597094 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0954. Min Act: -0.0001

Data Index: 678491 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0905. Min Act: -0.0001

Data Index: 228618 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0949. Min Act: -0.0001

Data Index: 28141 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1552888 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0895. Min Act: -0.0001

Data Index: 599973 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0872. Min Act: -0.0001

Data Index: 540892 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1651. Min Range: -0.1651

Max Act: 0.0996. Min Act: -0.0001

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 658