Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 917 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0052. Min Range: -3.0052

Max Act: 3.0052. Min Act: -0.0000

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.6872. Min Act: -0.0000

Data Index: 452754 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.6928. Min Act: -0.0000

Data Index: 464108 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.5048. Min Act: -0.0000

Data Index: 135404 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.5554. Min Act: -0.0000

Data Index: 589319 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.5637. Min Act: 0.0000

Data Index: 183146 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3952. Min Act: -0.0000

Data Index: 601174 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.5105. Min Act: -0.0000

Data Index: 255028 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3945. Min Act: -0.0000

Data Index: 852137 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1150477 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3491. Min Act: -0.0000

Data Index: 1328683 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3257. Min Act: -0.0000

Data Index: 214715 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.3154. Min Act: -0.0000

Data Index: 120139 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.1845. Min Act: -0.0000

Data Index: 507500 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.1195. Min Act: -0.0000

Data Index: 1205297 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.2419. Min Act: -0.0000

Data Index: 977869 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.2140. Min Act: -0.0000

Data Index: 1123114 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.0713. Min Act: -0.0000

Data Index: 981014 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.1265. Min Act: -0.0000

Data Index: 633789 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 3.0052. Min Range: -3.0052

Max Act: 2.2306. Min Act: -0.0000

Data Index: 190717 (C4 (Web Text))

Max Activating Token Index: 582