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

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

Neuron 3067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.4721. Min Act: -0.0001

Data Index: 134902 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.3950. Min Act: -0.0001

Data Index: 1110115 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2009. Min Act: -0.0001

Data Index: 1633010 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2094. Min Act: -0.0001

Data Index: 207646 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1821. Min Act: -0.0001

Data Index: 1172229 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1744. Min Act: -0.0001

Data Index: 1426645 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1098624 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1952. Min Act: -0.0001

Data Index: 935387 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1557. Min Act: -0.0001

Data Index: 211332 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1677. Min Act: -0.0001

Data Index: 1007396 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1004. Min Act: -0.0001

Data Index: 793905 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1071. Min Act: -0.0001

Data Index: 822256 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1550. Min Act: -0.0001

Data Index: 107124 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1607. Min Act: -0.0001

Data Index: 922939 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1218. Min Act: -0.0001

Data Index: 118920 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1431. Min Act: -0.0001

Data Index: 681253 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1208. Min Act: -0.0001

Data Index: 282877 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.0295. Min Act: -0.0001

Data Index: 1533190 (Python Code)

Max Activating Token Index: 310

Text #18

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1286. Min Act: -0.0001

Data Index: 354267 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.0196. Min Act: -0.0001

Data Index: 192395 (C4 (Web Text))

Max Activating Token Index: 1004