Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3085 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8860. Min Act: -0.0002

Data Index: 927829 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8377. Min Act: -0.0002

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8257. Min Act: -0.0002

Data Index: 1136511 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7949. Min Act: -0.0002

Data Index: 876946 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8512. Min Act: -0.0002

Data Index: 249225 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7626. Min Act: -0.0002

Data Index: 416845 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8959. Min Act: -0.0002

Data Index: 155971 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8619. Min Act: -0.0002

Data Index: 768023 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7662. Min Act: -0.0002

Data Index: 370189 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8637. Min Act: -0.0002

Data Index: 373373 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7531. Min Act: -0.0002

Data Index: 1096650 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8385. Min Act: -0.0002

Data Index: 684767 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8581. Min Act: -0.0002

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.9055. Min Act: -0.0002

Data Index: 1213950 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7634. Min Act: -0.0002

Data Index: 344006 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8482. Min Act: -0.0002

Data Index: 127006 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8809. Min Act: -0.0002

Data Index: 649780 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7002. Min Act: -0.0002

Data Index: 966975 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7904. Min Act: -0.0002

Data Index: 1144473 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.6557. Min Act: -0.0002

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 660