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

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

Neuron 4760 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: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0002

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0646. Min Act: -0.0002

Data Index: 65000 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0563. Min Act: -0.0002

Data Index: 498333 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0540. Min Act: -0.0002

Data Index: 846356 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0517. Min Act: -0.0002

Data Index: 299470 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0503. Min Act: -0.0002

Data Index: 396746 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0503. Min Act: -0.0002

Data Index: 208915 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0517. Min Act: -0.0002

Data Index: 268216 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0521. Min Act: -0.0002

Data Index: 244170 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0496. Min Act: -0.0002

Data Index: 935380 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0496. Min Act: -0.0002

Data Index: 138136 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0494. Min Act: -0.0002

Data Index: 66492 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1345735 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0503. Min Act: -0.0002

Data Index: 529569 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1096461 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1174190 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1209036 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0476. Min Act: -0.0002

Data Index: 617251 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0481. Min Act: -0.0003

Data Index: 505140 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0469. Min Act: -0.0002

Data Index: 798832 (C4 (Web Text))

Max Activating Token Index: 86