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

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

Neuron 603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.6884. Min Act: -0.0000

Data Index: 556802 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1047329 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.4663. Min Act: -0.0000

Data Index: 746857 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1357076 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1191900 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2533. Min Act: -0.0000

Data Index: 752003 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2594. Min Act: -0.0000

Data Index: 614118 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1717. Min Act: -0.0000

Data Index: 904984 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1665. Min Act: -0.0000

Data Index: 48657 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1082716 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1203. Min Act: -0.0000

Data Index: 59547 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1640. Min Act: -0.0000

Data Index: 162154 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1091543 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1188. Min Act: -0.0000

Data Index: 671786 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0523. Min Act: -0.0000

Data Index: 207833 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1007129 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0224. Min Act: -0.0000

Data Index: 284752 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0567. Min Act: -0.0000

Data Index: 16774 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.6884. Min Range: -1.6884

Max Act: 0.9868. Min Act: -0.0000

Data Index: 762774 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 1.6884. Min Range: -1.6884

Max Act: 0.9252. Min Act: -0.0000

Data Index: 1176841 (C4 (Web Text))

Max Activating Token Index: 795