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

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

Neuron 1131 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: 1.0401. Min Range: -1.0401

Max Act: 1.0401. Min Act: -0.0001

Data Index: 724943 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8920. Min Act: -0.0001

Data Index: 772490 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8825. Min Act: -0.0001

Data Index: 754711 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.8172. Min Act: -0.0001

Data Index: 621446 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7646. Min Act: -0.0001

Data Index: 936159 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7407. Min Act: -0.0001

Data Index: 341392 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1225980 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6969. Min Act: -0.0001

Data Index: 291863 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7344. Min Act: -0.0001

Data Index: 457999 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1055051 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7317. Min Act: -0.0001

Data Index: 426446 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7034. Min Act: -0.0001

Data Index: 1091372 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7281. Min Act: -0.0001

Data Index: 530337 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1313268 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.7068. Min Act: -0.0001

Data Index: 62872 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6806. Min Act: -0.0001

Data Index: 455597 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6951. Min Act: -0.0001

Data Index: 708311 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1207534 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6745. Min Act: -0.0001

Data Index: 459853 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 1.0401. Min Range: -1.0401

Max Act: 0.6795. Min Act: -0.0001

Data Index: 613178 (C4 (Web Text))

Max Activating Token Index: 185