Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3126 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0642. Min Act: -0.0001

Data Index: 314242 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0267. Min Act: -0.0001

Data Index: 989662 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0791. Min Act: -0.0001

Data Index: 928849 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0083. Min Act: -0.0001

Data Index: 1129400 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0240. Min Act: -0.0001

Data Index: 1270257 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0521. Min Act: -0.0001

Data Index: 704430 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0081. Min Act: -0.0001

Data Index: 839626 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.0791. Min Range: -1.0791

Max Act: 1.0257. Min Act: -0.0001

Data Index: 1295354 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9606. Min Act: -0.0001

Data Index: 461912 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9425. Min Act: -0.0001

Data Index: 699900 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9887. Min Act: -0.0001

Data Index: 131737 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9620. Min Act: -0.0001

Data Index: 697520 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1249060 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.8929. Min Act: -0.0001

Data Index: 732641 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.9148. Min Act: -0.0001

Data Index: 432163 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.8968. Min Act: -0.0001

Data Index: 930189 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.8655. Min Act: -0.0001

Data Index: 1059722 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.7926. Min Act: -0.0001

Data Index: 601542 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.8153. Min Act: -0.0001

Data Index: 812009 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.0791. Min Range: -1.0791

Max Act: 0.8789. Min Act: -0.0001

Data Index: 1441131 (Python Code)

Max Activating Token Index: 955