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

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

Neuron 4337 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3979. Min Range: -4.3979

Max Act: 4.3979. Min Act: -0.0000

Data Index: 1056233 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.9659. Min Act: -0.0000

Data Index: 91800 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.7886. Min Act: -0.0000

Data Index: 556628 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.6885. Min Act: -0.0000

Data Index: 193302 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.7032. Min Act: -0.0000

Data Index: 328836 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.6348. Min Act: -0.0000

Data Index: 1044795 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.4404. Min Act: -0.0000

Data Index: 672130 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.2831. Min Act: -0.0000

Data Index: 787595 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.0081. Min Act: -0.0000

Data Index: 529269 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.4551. Min Act: -0.0000

Data Index: 207055 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.1185. Min Act: -0.0000

Data Index: 118505 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.4289. Min Act: -0.0000

Data Index: 242169 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.2560. Min Act: -0.0000

Data Index: 610671 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.3517. Min Act: -0.0000

Data Index: 1152131 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.1775. Min Act: -0.0000

Data Index: 1224711 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.3029. Min Act: -0.0000

Data Index: 449813 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.1190. Min Act: -0.0000

Data Index: 435906 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.1208. Min Act: -0.0000

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.1214. Min Act: -0.0000

Data Index: 546298 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 4.3979. Min Range: -4.3979

Max Act: 3.0982. Min Act: -0.0000

Data Index: 1347860 (C4 (Web Text))

Max Activating Token Index: 741