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

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

Neuron 3815 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: 1.2822. Min Range: -1.2822

Max Act: 1.2822. Min Act: -0.0001

Data Index: 1256799 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.1161. Min Act: -0.0001

Data Index: 1207932 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9954. Min Act: -0.0001

Data Index: 408224 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.9899. Min Act: -0.0001

Data Index: 661916 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0404. Min Act: -0.0001

Data Index: 1182429 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 1.2822. Min Range: -1.2822

Max Act: 1.0135. Min Act: -0.0001

Data Index: 422234 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8742. Min Act: -0.0001

Data Index: 912693 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1309401 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8773. Min Act: -0.0001

Data Index: 1341153 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8883. Min Act: -0.0001

Data Index: 649601 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1006214 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8247. Min Act: -0.0001

Data Index: 1347441 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8754. Min Act: -0.0001

Data Index: 345996 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.7925. Min Act: -0.0001

Data Index: 773366 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8162. Min Act: -0.0001

Data Index: 1169799 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8636. Min Act: -0.0001

Data Index: 986017 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1121402 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8845. Min Act: -0.0001

Data Index: 1014950 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1301859 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.2822. Min Range: -1.2822

Max Act: 0.8401. Min Act: -0.0001

Data Index: 277158 (C4 (Web Text))

Max Activating Token Index: 746