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

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

Neuron 2726 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0000

Data Index: 51362 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7981. Min Act: -0.0000

Data Index: 105861 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1292618 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7809. Min Act: -0.0000

Data Index: 518355 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7545. Min Act: -0.0000

Data Index: 443457 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1236210 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7733. Min Act: -0.0000

Data Index: 668797 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7638. Min Act: -0.0000

Data Index: 528527 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7634. Min Act: -0.0000

Data Index: 169188 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6859. Min Act: -0.0000

Data Index: 142337 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7258. Min Act: -0.0000

Data Index: 463921 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6959. Min Act: -0.0000

Data Index: 332274 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1103511 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7184. Min Act: -0.0000

Data Index: 456350 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1278873 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7099. Min Act: -0.0000

Data Index: 542160 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7008. Min Act: -0.0000

Data Index: 62628 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6747. Min Act: -0.0000

Data Index: 941978 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7159. Min Act: -0.0000

Data Index: 94917 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7118. Min Act: -0.0000

Data Index: 154336 (C4 (Web Text))

Max Activating Token Index: 957