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

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

Neuron 3378 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.5912. Min Act: -0.0001

Data Index: 913131 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.4326. Min Act: -0.0000

Data Index: 820119 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.0910. Min Act: -0.0000

Data Index: 349186 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.2975. Min Act: -0.0001

Data Index: 689922 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.1196. Min Act: -0.0001

Data Index: 242897 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.2642. Min Act: -0.0000

Data Index: 1112042 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.2044. Min Act: -0.0000

Data Index: 1002035 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.4996. Min Act: -0.0000

Data Index: 64816 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1308567 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.1366. Min Act: -0.0000

Data Index: 577024 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.1132. Min Act: -0.0000

Data Index: 909644 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.1004. Min Act: -0.0000

Data Index: 782960 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.5222. Min Act: -0.0001

Data Index: 988266 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.9691. Min Act: -0.0000

Data Index: 224760 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.8526. Min Act: -0.0000

Data Index: 425727 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.7947. Min Act: -0.0001

Data Index: 837618 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.5413. Min Act: -0.0001

Data Index: 1160003 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1130910 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.5912. Min Range: -3.5912

Max Act: 3.1668. Min Act: -0.0000

Data Index: 1042572 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 3.5912. Min Range: -3.5912

Max Act: 2.3055. Min Act: -0.0000

Data Index: 778768 (C4 (Web Text))

Max Activating Token Index: 85