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

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

Neuron 789 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8197. Min Range: -2.8197

Max Act: 2.8197. Min Act: -0.0000

Data Index: 1328464 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 2.8197. Min Range: -2.8197

Max Act: 2.3733. Min Act: -0.0000

Data Index: 1156722 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 2.8197. Min Range: -2.8197

Max Act: 2.3462. Min Act: -0.0000

Data Index: 65047 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 2.8197. Min Range: -2.8197

Max Act: 2.0949. Min Act: -0.0000

Data Index: 1114126 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.9141. Min Act: -0.0000

Data Index: 908002 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.8197. Min Range: -2.8197

Max Act: 2.2160. Min Act: -0.0000

Data Index: 663093 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.7370. Min Act: -0.0000

Data Index: 592437 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.8192. Min Act: -0.0000

Data Index: 669147 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.7450. Min Act: -0.0000

Data Index: 1243505 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.5573. Min Act: -0.0000

Data Index: 595264 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.5996. Min Act: -0.0000

Data Index: 741327 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.8116. Min Act: -0.0000

Data Index: 519154 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.5901. Min Act: -0.0000

Data Index: 667615 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.5591. Min Act: -0.0000

Data Index: 101758 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.4778. Min Act: -0.0000

Data Index: 139375 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.7096. Min Act: -0.0000

Data Index: 676583 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.3355. Min Act: -0.0000

Data Index: 993911 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.3518. Min Act: -0.0000

Data Index: 106158 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.4639. Min Act: -0.0000

Data Index: 487767 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.8197. Min Range: -2.8197

Max Act: 1.4381. Min Act: -0.0000

Data Index: 252957 (C4 (Web Text))

Max Activating Token Index: 644