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

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

Neuron 2969 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1374. Min Act: -0.0001

Data Index: 200126 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1781. Min Act: -0.0001

Data Index: 47379 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.2105. Min Act: -0.0001

Data Index: 1292897 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1240. Min Act: -0.0001

Data Index: 115451 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1298. Min Act: -0.0001

Data Index: 375569 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1005. Min Act: -0.0001

Data Index: 451904 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1298. Min Act: -0.0001

Data Index: 1114815 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.1156. Min Act: -0.0001

Data Index: 906202 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0881. Min Act: -0.0001

Data Index: 762275 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0221. Min Act: -0.0001

Data Index: 1033113 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.2105. Min Range: -1.2105

Max Act: 0.9061. Min Act: -0.0001

Data Index: 939541 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0590. Min Act: -0.0001

Data Index: 1157798 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.2105. Min Range: -1.2105

Max Act: 0.9716. Min Act: -0.0001

Data Index: 1502517 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0229. Min Act: -0.0001

Data Index: 932840 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.2105. Min Range: -1.2105

Max Act: 0.9212. Min Act: -0.0001

Data Index: 1637503 (Python Code)

Max Activating Token Index: 976

Text #15

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0258. Min Act: -0.0001

Data Index: 643191 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 1.2105. Min Range: -1.2105

Max Act: 0.9851. Min Act: -0.0001

Data Index: 1070756 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0771. Min Act: -0.0001

Data Index: 577081 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.2105. Min Range: -1.2105

Max Act: 0.8897. Min Act: -0.0001

Data Index: 212880 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.2105. Min Range: -1.2105

Max Act: 1.0362. Min Act: -0.0001

Data Index: 19447 (C4 (Web Text))

Max Activating Token Index: 910