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

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

Neuron 1004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.4623. Min Act: -0.0001

Data Index: 890576 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.3085. Min Act: -0.0001

Data Index: 1106388 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.4582. Min Act: -0.0001

Data Index: 314082 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.3458. Min Act: -0.0001

Data Index: 522205 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1742. Min Act: -0.0001

Data Index: 1325430 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.2577. Min Act: -0.0001

Data Index: 104359 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1727. Min Act: -0.0001

Data Index: 614023 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1968. Min Act: -0.0001

Data Index: 543497 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.0853. Min Act: -0.0001

Data Index: 1084501 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.0785. Min Act: -0.0001

Data Index: 537650 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1089. Min Act: -0.0001

Data Index: 429917 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1002. Min Act: -0.0001

Data Index: 802743 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.2312. Min Act: -0.0001

Data Index: 1099506 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.0925. Min Act: -0.0000

Data Index: 198710 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1257. Min Act: -0.0001

Data Index: 599741 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1496. Min Act: -0.0001

Data Index: 343606 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.4623. Min Range: -1.4623

Max Act: 0.9983. Min Act: -0.0001

Data Index: 25715 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.0222. Min Act: -0.0001

Data Index: 66409 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.1522. Min Act: -0.0001

Data Index: 1028168 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 1.4623. Min Range: -1.4623

Max Act: 1.0656. Min Act: -0.0001

Data Index: 993461 (C4 (Web Text))

Max Activating Token Index: 1003