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

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

Neuron 5201 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: 2.7683. Min Range: -2.7683

Max Act: 2.7683. Min Act: -0.0000

Data Index: 864624 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 2.7683. Min Range: -2.7683

Max Act: 2.4059. Min Act: -0.0000

Data Index: 1255390 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 2.7683. Min Range: -2.7683

Max Act: 2.1644. Min Act: -0.0001

Data Index: 373869 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 2.7683. Min Range: -2.7683

Max Act: 2.0955. Min Act: -0.0000

Data Index: 950606 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 2.7683. Min Range: -2.7683

Max Act: 2.1026. Min Act: -0.0000

Data Index: 324944 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 2.7683. Min Range: -2.7683

Max Act: 2.0836. Min Act: -0.0000

Data Index: 151207 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1051347 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.7856. Min Act: -0.0001

Data Index: 653227 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.8255. Min Act: -0.0000

Data Index: 961963 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.8451. Min Act: -0.0000

Data Index: 501318 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.7812. Min Act: -0.0000

Data Index: 560129 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1249354 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.7292. Min Act: -0.0000

Data Index: 771941 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.7141. Min Act: -0.0000

Data Index: 155586 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.6234. Min Act: -0.0000

Data Index: 1102793 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.6818. Min Act: -0.0000

Data Index: 371260 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.5840. Min Act: -0.0000

Data Index: 429989 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.6722. Min Act: -0.0000

Data Index: 1271697 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.6159. Min Act: -0.0001

Data Index: 304052 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 2.7683. Min Range: -2.7683

Max Act: 1.5157. Min Act: -0.0000

Data Index: 521153 (C4 (Web Text))

Max Activating Token Index: 579