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

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

Neuron 1615 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0181. Min Range: -1.0181

Max Act: 1.0181. Min Act: -0.0001

Data Index: 102002 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.8747. Min Act: -0.0001

Data Index: 445373 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.8200. Min Act: -0.0001

Data Index: 951461 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7606. Min Act: -0.0001

Data Index: 1286139 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.8322. Min Act: -0.0001

Data Index: 583232 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7549. Min Act: -0.0001

Data Index: 605858 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7815. Min Act: -0.0001

Data Index: 441071 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7485. Min Act: -0.0001

Data Index: 762788 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7217. Min Act: -0.0001

Data Index: 466693 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1077442 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7220. Min Act: -0.0001

Data Index: 1007545 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6963. Min Act: -0.0001

Data Index: 131793 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7264. Min Act: -0.0001

Data Index: 266064 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.7251. Min Act: -0.0001

Data Index: 1222896 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6708. Min Act: -0.0001

Data Index: 501942 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6300. Min Act: -0.0001

Data Index: 986940 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1011396 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6287. Min Act: -0.0001

Data Index: 728482 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.6472. Min Act: -0.0001

Data Index: 180033 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 1.0181. Min Range: -1.0181

Max Act: 0.5936. Min Act: -0.0001

Data Index: 886343 (C4 (Web Text))

Max Activating Token Index: 944