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

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

Neuron 1247 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.7140. Min Act: -0.0002

Data Index: 1324959 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5987. Min Act: -0.0002

Data Index: 1080120 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5314. Min Act: -0.0002

Data Index: 1308365 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5730. Min Act: -0.0002

Data Index: 465067 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4914. Min Act: -0.0002

Data Index: 881967 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5363. Min Act: -0.0002

Data Index: 459879 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5056. Min Act: -0.0002

Data Index: 280796 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5002. Min Act: -0.0002

Data Index: 188652 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4874. Min Act: -0.0002

Data Index: 1094124 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4899. Min Act: -0.0002

Data Index: 1199158 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5271. Min Act: -0.0002

Data Index: 887697 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4510. Min Act: -0.0002

Data Index: 1035943 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4256. Min Act: -0.0002

Data Index: 1177775 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4341. Min Act: -0.0002

Data Index: 39932 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4269. Min Act: -0.0002

Data Index: 861086 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4449. Min Act: -0.0002

Data Index: 844442 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4152. Min Act: -0.0002

Data Index: 99197 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4130. Min Act: -0.0002

Data Index: 558426 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4089. Min Act: -0.0002

Data Index: 963714 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4480. Min Act: -0.0002

Data Index: 1310769 (C4 (Web Text))

Max Activating Token Index: 766