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

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

Neuron 3477 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2061. Min Act: -0.0002

Data Index: 96602 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2184. Min Act: -0.0002

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.2237. Min Act: -0.0002

Data Index: 213978 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1834. Min Act: -0.0003

Data Index: 598674 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1715. Min Act: -0.0002

Data Index: 235821 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1988. Min Act: -0.0002

Data Index: 1253496 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1588. Min Act: -0.0002

Data Index: 817927 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1614. Min Act: -0.0002

Data Index: 388565 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1743. Min Act: -0.0002

Data Index: 825851 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1566. Min Act: -0.0002

Data Index: 888451 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1445. Min Act: -0.0002

Data Index: 1140703 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1324. Min Act: -0.0002

Data Index: 841653 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1166. Min Act: -0.0002

Data Index: 1175735 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1163. Min Act: -0.0002

Data Index: 589171 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0822. Min Act: -0.0002

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1194. Min Act: -0.0002

Data Index: 1291754 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.1111. Min Act: -0.0002

Data Index: 602569 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0859. Min Act: -0.0002

Data Index: 1207136 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0883. Min Act: -0.0002

Data Index: 40956 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.2237. Min Range: -1.2237

Max Act: 1.0993. Min Act: -0.0002

Data Index: 386120 (C4 (Web Text))

Max Activating Token Index: 4