Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1074 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0409. Min Act: -0.0001

Data Index: 622007 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0451. Min Act: -0.0001

Data Index: 336090 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.1211. Min Act: -0.0001

Data Index: 331835 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0311. Min Act: -0.0001

Data Index: 1139944 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9570. Min Act: -0.0001

Data Index: 508271 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9646. Min Act: -0.0001

Data Index: 2806 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9652. Min Act: -0.0001

Data Index: 852432 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8507. Min Act: -0.0001

Data Index: 467008 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9204. Min Act: -0.0001

Data Index: 894818 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8924. Min Act: -0.0001

Data Index: 311467 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8770. Min Act: -0.0001

Data Index: 223695 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8005. Min Act: -0.0001

Data Index: 1105744 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9190. Min Act: -0.0001

Data Index: 1312109 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8827. Min Act: -0.0001

Data Index: 400403 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8579. Min Act: -0.0001

Data Index: 503724 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8528. Min Act: -0.0001

Data Index: 1032521 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8755. Min Act: -0.0001

Data Index: 760816 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8401. Min Act: -0.0001

Data Index: 55768 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.8188. Min Act: -0.0001

Data Index: 575493 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.7412. Min Act: -0.0001

Data Index: 1062435 (C4 (Web Text))

Max Activating Token Index: 870