Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5626 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1545830 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1553461 (Python Code)

Max Activating Token Index: 674

Text #2

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1271. Min Act: -0.0002

Data Index: 825608 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1218. Min Act: -0.0002

Data Index: 1593705 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1400411 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1381916 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1421063 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1492639 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1291685 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1481864 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.1035. Min Act: -0.0002

Data Index: 453849 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1633073 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1425113 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0969. Min Act: -0.0002

Data Index: 380840 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1503144 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1267067 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0920. Min Act: -0.0002

Data Index: 714052 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0951. Min Act: -0.0002

Data Index: 339865 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1626546 (Python Code)

Max Activating Token Index: 645

Text #19

Max Range: 0.1498. Min Range: -0.1498

Max Act: 0.0905. Min Act: -0.0002

Data Index: 437193 (C4 (Web Text))

Max Activating Token Index: 383