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

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

Neuron 4368 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: 0.4025. Min Range: -0.4025

Max Act: 0.3998. Min Act: -0.0001

Data Index: 1262564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.4025. Min Act: -0.0001

Data Index: 1030086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3946. Min Act: -0.0001

Data Index: 676020 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3943. Min Act: -0.0001

Data Index: 360371 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3849. Min Act: -0.0001

Data Index: 710519 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3898. Min Act: -0.0001

Data Index: 706015 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3677. Min Act: -0.0001

Data Index: 505480 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3725. Min Act: -0.0001

Data Index: 739074 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3730. Min Act: -0.0001

Data Index: 785381 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3654. Min Act: -0.0001

Data Index: 1330230 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3641. Min Act: -0.0001

Data Index: 179430 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3642. Min Act: -0.0001

Data Index: 867511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1052585 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3711. Min Act: -0.0001

Data Index: 1282724 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1049871 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3671. Min Act: -0.0001

Data Index: 24234 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3602. Min Act: -0.0001

Data Index: 26228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1094016 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1359052 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.4025. Min Range: -0.4025

Max Act: 0.3551. Min Act: -0.0001

Data Index: 322419 (C4 (Web Text))

Max Activating Token Index: 1023