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

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

Neuron 5615 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9061. Min Range: -2.9061

Max Act: 2.9061. Min Act: -0.0000

Data Index: 550232 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.8544. Min Act: -0.0000

Data Index: 115871 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.9025. Min Act: -0.0000

Data Index: 890081 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.7177. Min Act: -0.0000

Data Index: 1171971 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.7016. Min Act: -0.0000

Data Index: 857384 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6180. Min Act: -0.0000

Data Index: 1274503 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6140. Min Act: -0.0000

Data Index: 130147 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6865. Min Act: -0.0000

Data Index: 998684 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6470. Min Act: -0.0000

Data Index: 93567 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6591. Min Act: -0.0000

Data Index: 474863 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.5576. Min Act: -0.0000

Data Index: 810616 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.7176. Min Act: -0.0000

Data Index: 1254878 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6453. Min Act: -0.0000

Data Index: 560941 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6330. Min Act: -0.0000

Data Index: 227042 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6392. Min Act: -0.0000

Data Index: 662635 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.7101. Min Act: -0.0000

Data Index: 460972 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6246. Min Act: -0.0000

Data Index: 464998 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.5927. Min Act: -0.0000

Data Index: 348748 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6095. Min Act: -0.0000

Data Index: 420486 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 2.9061. Min Range: -2.9061

Max Act: 1.6827. Min Act: -0.0000

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 293