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

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

Neuron 1028 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2291. Min Act: -0.0001

Data Index: 254103 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1729. Min Act: -0.0001

Data Index: 1141040 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2623. Min Act: -0.0001

Data Index: 432261 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2254. Min Act: -0.0001

Data Index: 855564 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.1904. Min Act: -0.0001

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0499. Min Act: -0.0001

Data Index: 624991 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.2106. Min Act: -0.0000

Data Index: 592910 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0331. Min Act: -0.0001

Data Index: 28080 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0052. Min Act: -0.0001

Data Index: 533212 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0330. Min Act: -0.0001

Data Index: 1197540 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0113. Min Act: -0.0001

Data Index: 55029 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9483. Min Act: -0.0001

Data Index: 254296 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9973. Min Act: -0.0001

Data Index: 464120 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9014. Min Act: -0.0001

Data Index: 1120343 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.8954. Min Act: -0.0001

Data Index: 904276 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9818. Min Act: -0.0001

Data Index: 481172 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9844. Min Act: -0.0001

Data Index: 913211 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0623. Min Act: -0.0001

Data Index: 6530 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.2623. Min Range: -1.2623

Max Act: 1.0118. Min Act: -0.0001

Data Index: 469161 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 1.2623. Min Range: -1.2623

Max Act: 0.9434. Min Act: -0.0001

Data Index: 177974 (C4 (Web Text))

Max Activating Token Index: 472