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

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

Neuron 5625 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1155. Min Range: -1.1155

Max Act: 1.1155. Min Act: -0.0000

Data Index: 609055 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 1.1155. Min Range: -1.1155

Max Act: 1.0403. Min Act: -0.0000

Data Index: 955019 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9091. Min Act: -0.0000

Data Index: 853908 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.9330. Min Act: -0.0000

Data Index: 927291 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8596. Min Act: -0.0000

Data Index: 661734 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1107501 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8713. Min Act: -0.0000

Data Index: 677602 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8169. Min Act: -0.0000

Data Index: 390754 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8201. Min Act: -0.0000

Data Index: 97040 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7785. Min Act: -0.0000

Data Index: 1179658 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.8135. Min Act: -0.0000

Data Index: 635681 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7630. Min Act: -0.0000

Data Index: 380291 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1046138 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1246401 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7193. Min Act: -0.0000

Data Index: 463115 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1184885 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.6822. Min Act: -0.0000

Data Index: 783389 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1033867 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.6586. Min Act: -0.0000

Data Index: 46251 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.1155. Min Range: -1.1155

Max Act: 0.6511. Min Act: -0.0000

Data Index: 113361 (C4 (Web Text))

Max Activating Token Index: 474