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

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

Neuron 3464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4011. Min Act: -0.0000

Data Index: 913781 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1314072 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.4144. Min Act: -0.0000

Data Index: 342849 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3842. Min Act: -0.0000

Data Index: 496659 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1039851 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1844. Min Act: -0.0000

Data Index: 911871 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.3323. Min Act: -0.0000

Data Index: 722176 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1517. Min Act: -0.0000

Data Index: 437014 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2462. Min Act: -0.0000

Data Index: 817178 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2603. Min Act: -0.0001

Data Index: 511838 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2009. Min Act: -0.0000

Data Index: 220917 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1279. Min Act: -0.0000

Data Index: 159331 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1305080 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1317192 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2684. Min Act: -0.0000

Data Index: 90198 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.2147. Min Act: -0.0000

Data Index: 63677 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1092. Min Act: -0.0000

Data Index: 1139151 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1468. Min Act: -0.0000

Data Index: 472743 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.1623. Min Act: -0.0000

Data Index: 237543 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1134774 (C4 (Web Text))

Max Activating Token Index: 226