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

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

Neuron 4311 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: 1.0873. Min Range: -1.0873

Max Act: 1.0873. Min Act: -0.0000

Data Index: 457826 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.0873. Min Range: -1.0873

Max Act: 1.0353. Min Act: -0.0000

Data Index: 274469 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9339. Min Act: -0.0001

Data Index: 212859 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.0873. Min Range: -1.0873

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1542374 (Python Code)

Max Activating Token Index: 335

Text #4

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9689. Min Act: -0.0000

Data Index: 829101 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9278. Min Act: -0.0000

Data Index: 186250 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9388. Min Act: -0.0001

Data Index: 1076799 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9248. Min Act: -0.0001

Data Index: 130677 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.9073. Min Act: -0.0000

Data Index: 202488 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8746. Min Act: -0.0001

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1255118 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8653. Min Act: -0.0000

Data Index: 210776 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8128. Min Act: -0.0000

Data Index: 83674 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8643. Min Act: -0.0000

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8658. Min Act: -0.0001

Data Index: 497736 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1508187 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8127. Min Act: -0.0001

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1420652 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 1.0873. Min Range: -1.0873

Max Act: 0.8961. Min Act: -0.0001

Data Index: 990612 (C4 (Web Text))

Max Activating Token Index: 768