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

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

Neuron 2204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3926. Min Act: -0.0001

Data Index: 234396 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3450. Min Act: -0.0001

Data Index: 845485 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3263. Min Act: -0.0001

Data Index: 694725 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3349. Min Act: -0.0001

Data Index: 1157655 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3160. Min Act: -0.0001

Data Index: 23673 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3054. Min Act: -0.0001

Data Index: 183504 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1002079 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3087. Min Act: -0.0001

Data Index: 443813 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3006. Min Act: -0.0001

Data Index: 662402 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2773. Min Act: -0.0001

Data Index: 362358 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2881. Min Act: -0.0001

Data Index: 470952 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2825. Min Act: -0.0001

Data Index: 18378 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2769. Min Act: -0.0001

Data Index: 992499 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2895. Min Act: -0.0001

Data Index: 256944 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2976. Min Act: -0.0001

Data Index: 835827 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.3062. Min Act: -0.0001

Data Index: 748761 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1360241 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2629. Min Act: -0.0001

Data Index: 1381971 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2954. Min Act: -0.0001

Data Index: 215498 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.3926. Min Range: -0.3926

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1521890 (Python Code)

Max Activating Token Index: 377