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

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

Neuron 3238 in Layer 0

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: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1179345 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0737. Min Act: -0.0001

Data Index: 18827 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0724. Min Act: -0.0002

Data Index: 472533 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0710. Min Act: -0.0001

Data Index: 116006 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0688. Min Act: -0.0001

Data Index: 246307 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0681. Min Act: -0.0001

Data Index: 870936 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0683. Min Act: -0.0001

Data Index: 910979 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0680. Min Act: -0.0001

Data Index: 234124 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0648. Min Act: -0.0001

Data Index: 316639 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0626. Min Act: -0.0001

Data Index: 281271 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0636. Min Act: -0.0001

Data Index: 563352 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0629. Min Act: -0.0001

Data Index: 361313 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0617. Min Act: -0.0001

Data Index: 973982 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0618. Min Act: -0.0001

Data Index: 78854 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0602. Min Act: -0.0001

Data Index: 554555 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0593. Min Act: -0.0001

Data Index: 328737 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0598. Min Act: -0.0001

Data Index: 709845 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0589. Min Act: -0.0001

Data Index: 913412 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1161254 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0581. Min Act: -0.0001

Data Index: 818339 (C4 (Web Text))

Max Activating Token Index: 109