Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.1224. Min Act: -0.0000

Data Index: 666071 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.1218. Min Act: -0.0000

Data Index: 97330 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0637. Min Act: -0.0000

Data Index: 736123 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1015725 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0413. Min Act: -0.0000

Data Index: 902854 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9994. Min Act: -0.0001

Data Index: 798285 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9813. Min Act: -0.0000

Data Index: 849492 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 1.1224. Min Range: -1.1224

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1177994 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9705. Min Act: -0.0001

Data Index: 573430 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9716. Min Act: 0.0000

Data Index: 685977 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9121. Min Act: -0.0000

Data Index: 848940 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1015414 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1016194 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1201165 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1347517 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8557. Min Act: -0.0000

Data Index: 957939 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8877. Min Act: -0.0000

Data Index: 507812 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8751. Min Act: -0.0000

Data Index: 599367 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8700. Min Act: -0.0000

Data Index: 257676 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.1224. Min Range: -1.1224

Max Act: 0.8426. Min Act: -0.0000

Data Index: 826315 (C4 (Web Text))

Max Activating Token Index: 210