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

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

Neuron 1512 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.5099. Min Act: -0.0001

Data Index: 657516 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4656. Min Act: -0.0001

Data Index: 288313 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4048. Min Act: -0.0001

Data Index: 1187502 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4883. Min Act: -0.0001

Data Index: 428134 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4801. Min Act: -0.0001

Data Index: 1191267 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4407. Min Act: -0.0001

Data Index: 1045596 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4238. Min Act: -0.0001

Data Index: 885021 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1165930 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4211. Min Act: -0.0001

Data Index: 846202 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3925. Min Act: -0.0001

Data Index: 46654 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4099. Min Act: -0.0001

Data Index: 934404 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4398. Min Act: -0.0001

Data Index: 485001 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4254. Min Act: -0.0001

Data Index: 528471 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1118964 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3955. Min Act: -0.0001

Data Index: 767572 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3921. Min Act: -0.0001

Data Index: 939828 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3919. Min Act: -0.0001

Data Index: 235742 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4066. Min Act: -0.0001

Data Index: 360304 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.4021. Min Act: -0.0001

Data Index: 1195924 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.5099. Min Range: -0.5099

Max Act: 0.3523. Min Act: -0.0001

Data Index: 636005 (C4 (Web Text))

Max Activating Token Index: 280