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

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

Neuron 2710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1680. Min Range: -4.1680

Max Act: 4.1680. Min Act: -0.0001

Data Index: 451816 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.8086. Min Act: -0.0001

Data Index: 1284928 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.5047. Min Act: -0.0001

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.5053. Min Act: -0.0001

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.4641. Min Act: -0.0001

Data Index: 678975 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.2983. Min Act: -0.0001

Data Index: 748201 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.5398. Min Act: -0.0000

Data Index: 346982 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.5976. Min Act: -0.0000

Data Index: 259213 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3841. Min Act: -0.0000

Data Index: 683879 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3430. Min Act: -0.0001

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.5081. Min Act: -0.0001

Data Index: 578411 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3291. Min Act: -0.0000

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3504. Min Act: -0.0001

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3462. Min Act: -0.0000

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.4928. Min Act: -0.0000

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.3064. Min Act: -0.0000

Data Index: 510287 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.0283. Min Act: -0.0000

Data Index: 557158 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.1584. Min Act: -0.0000

Data Index: 1311732 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.2787. Min Act: -0.0000

Data Index: 1353294 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 4.1680. Min Range: -4.1680

Max Act: 3.2791. Min Act: -0.0000

Data Index: 464553 (C4 (Web Text))

Max Activating Token Index: 307