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

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

Neuron 5489 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0814. Min Range: -5.0814

Max Act: 5.0702. Min Act: -0.0000

Data Index: 49914 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 5.0814. Min Range: -5.0814

Max Act: 5.0814. Min Act: -0.0000

Data Index: 937254 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.8756. Min Act: -0.0000

Data Index: 1197036 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.7977. Min Act: -0.0000

Data Index: 354598 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.7777. Min Act: -0.0000

Data Index: 351643 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.6688. Min Act: -0.0000

Data Index: 544120 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.6775. Min Act: -0.0000

Data Index: 539236 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.6209. Min Act: -0.0000

Data Index: 64418 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.9122. Min Act: -0.0000

Data Index: 1201072 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.4848. Min Act: -0.0000

Data Index: 892558 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.4182. Min Act: -0.0000

Data Index: 1274118 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.4172. Min Act: -0.0000

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.4245. Min Act: -0.0000

Data Index: 855879 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.3591. Min Act: -0.0000

Data Index: 704474 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.2078. Min Act: -0.0000

Data Index: 139888 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.3307. Min Act: -0.0000

Data Index: 589975 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.3279. Min Act: -0.0000

Data Index: 854582 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.4909. Min Act: -0.0000

Data Index: 201296 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.3009. Min Act: -0.0000

Data Index: 129855 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 5.0814. Min Range: -5.0814

Max Act: 4.1117. Min Act: -0.0000

Data Index: 1246500 (C4 (Web Text))

Max Activating Token Index: 923