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

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

Neuron 4327 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1266. Min Range: -3.1266

Max Act: 3.1266. Min Act: -0.0001

Data Index: 865299 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.9057. Min Act: -0.0001

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.2041. Min Act: -0.0000

Data Index: 339854 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5026. Min Act: -0.0001

Data Index: 567868 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7332. Min Act: -0.0001

Data Index: 41423 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.3437. Min Act: -0.0001

Data Index: 1331471 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6014. Min Act: -0.0001

Data Index: 956877 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.7116. Min Act: -0.0001

Data Index: 766021 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5141. Min Act: -0.0001

Data Index: 893796 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6505. Min Act: -0.0001

Data Index: 402092 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.4164. Min Act: -0.0001

Data Index: 538450 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.4777. Min Act: -0.0000

Data Index: 943490 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.3519. Min Act: -0.0001

Data Index: 99847 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.5979. Min Act: -0.0001

Data Index: 93232 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.2859. Min Act: -0.0000

Data Index: 1314184 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.2986. Min Act: -0.0000

Data Index: 1296544 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.6697. Min Act: -0.0001

Data Index: 154887 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.2662. Min Act: -0.0001

Data Index: 546221 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.1178. Min Act: -0.0000

Data Index: 600864 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.1266. Min Range: -3.1266

Max Act: 2.2830. Min Act: -0.0001

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 733