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

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

Neuron 2184 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0235. Min Range: -1.0235

Max Act: 1.0235. Min Act: -0.0001

Data Index: 719296 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9924. Min Act: -0.0001

Data Index: 189583 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9870. Min Act: -0.0001

Data Index: 358847 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1050626 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8592. Min Act: -0.0001

Data Index: 735797 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7763. Min Act: -0.0001

Data Index: 970594 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8300. Min Act: -0.0001

Data Index: 308864 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7931. Min Act: -0.0001

Data Index: 88174 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7836. Min Act: -0.0001

Data Index: 249996 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7613. Min Act: -0.0001

Data Index: 456816 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7224. Min Act: -0.0001

Data Index: 549219 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7487. Min Act: -0.0001

Data Index: 252974 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7534. Min Act: -0.0001

Data Index: 445354 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7170. Min Act: -0.0001

Data Index: 555662 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1321041 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7122. Min Act: -0.0001

Data Index: 1281661 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1289447 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7427. Min Act: -0.0001

Data Index: 927146 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.7466. Min Act: -0.0001

Data Index: 623138 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.0235. Min Range: -1.0235

Max Act: 0.6744. Min Act: -0.0001

Data Index: 487428 (C4 (Web Text))

Max Activating Token Index: 511