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

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

Neuron 4288 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1515. Min Act: -0.0000

Data Index: 747691 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.1122. Min Act: -0.0000

Data Index: 466029 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0755. Min Act: -0.0000

Data Index: 166948 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.1515. Min Range: -1.1515

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1293856 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9787. Min Act: -0.0000

Data Index: 217988 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1145354 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9662. Min Act: -0.0000

Data Index: 362874 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1053191 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1133850 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8896. Min Act: -0.0000

Data Index: 575624 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.7804. Min Act: -0.0000

Data Index: 344031 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8757. Min Act: -0.0000

Data Index: 943483 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8755. Min Act: -0.0000

Data Index: 77392 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9621. Min Act: -0.0000

Data Index: 580380 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8029. Min Act: -0.0000

Data Index: 487887 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8847. Min Act: -0.0000

Data Index: 506531 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8808. Min Act: -0.0000

Data Index: 914660 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.9250. Min Act: -0.0000

Data Index: 408009 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1343185 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.1515. Min Range: -1.1515

Max Act: 0.8632. Min Act: -0.0000

Data Index: 347759 (C4 (Web Text))

Max Activating Token Index: 731