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

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

Neuron 2114 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: 1.1200. Min Range: -1.1200

Max Act: 1.1200. Min Act: -0.0001

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.9291. Min Act: -0.0001

Data Index: 903491 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.9070. Min Act: -0.0001

Data Index: 503926 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.9326. Min Act: -0.0001

Data Index: 212960 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8823. Min Act: -0.0001

Data Index: 133751 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8949. Min Act: -0.0001

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.9180. Min Act: -0.0001

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8935. Min Act: -0.0001

Data Index: 314184 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8174. Min Act: -0.0001

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8343. Min Act: -0.0001

Data Index: 106332 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8853. Min Act: -0.0001

Data Index: 718346 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8533. Min Act: -0.0001

Data Index: 244961 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8509. Min Act: -0.0001

Data Index: 369230 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1017810 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8227. Min Act: -0.0001

Data Index: 840594 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8199. Min Act: -0.0001

Data Index: 188112 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8197. Min Act: -0.0001

Data Index: 1033614 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8164. Min Act: -0.0001

Data Index: 719258 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.7894. Min Act: -0.0001

Data Index: 406339 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.8083. Min Act: -0.0001

Data Index: 987106 (C4 (Web Text))

Max Activating Token Index: 215