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

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

Neuron 4266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0158. Min Range: -1.0158

Max Act: 1.0158. Min Act: -0.0000

Data Index: 102911 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8650. Min Act: -0.0000

Data Index: 996782 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8695. Min Act: -0.0000

Data Index: 725568 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8670. Min Act: -0.0000

Data Index: 461711 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1207108 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1205893 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1184025 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7711. Min Act: -0.0000

Data Index: 919491 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7632. Min Act: -0.0000

Data Index: 316182 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7326. Min Act: -0.0001

Data Index: 124956 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7275. Min Act: -0.0000

Data Index: 775053 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7466. Min Act: -0.0000

Data Index: 365763 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1094603 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7617. Min Act: -0.0000

Data Index: 784344 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1104325 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1162106 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1340765 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.6676. Min Act: -0.0000

Data Index: 38420 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.7051. Min Act: -0.0001

Data Index: 1171459 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.0158. Min Range: -1.0158

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1022710 (C4 (Web Text))

Max Activating Token Index: 632