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

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

Neuron 1443 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5863. Min Act: -0.0003

Data Index: 1052201 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4606. Min Act: -0.0003

Data Index: 372746 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4843. Min Act: -0.0003

Data Index: 108977 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4396. Min Act: -0.0003

Data Index: 987911 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3271. Min Act: -0.0003

Data Index: 118439 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3652. Min Act: -0.0003

Data Index: 444288 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.2950. Min Act: -0.0003

Data Index: 130873 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3263. Min Act: -0.0003

Data Index: 1129191 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3355. Min Act: -0.0003

Data Index: 1346128 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3476. Min Act: -0.0003

Data Index: 516133 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3670. Min Act: -0.0003

Data Index: 283937 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3775. Min Act: -0.0003

Data Index: 728600 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3168. Min Act: -0.0003

Data Index: 1110551 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3393. Min Act: -0.0003

Data Index: 226708 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3014. Min Act: -0.0003

Data Index: 958312 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3120. Min Act: -0.0003

Data Index: 1070340 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3219. Min Act: -0.0003

Data Index: 1149479 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3228. Min Act: -0.0003

Data Index: 698073 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3056. Min Act: -0.0003

Data Index: 23424 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.3275. Min Act: -0.0003

Data Index: 1107003 (C4 (Web Text))

Max Activating Token Index: 44