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

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

Neuron 3624 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1117053 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1274095 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1072635 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.4537. Min Act: -0.0000

Data Index: 626230 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2841. Min Act: -0.0000

Data Index: 448043 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2712. Min Act: -0.0000

Data Index: 912566 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2505. Min Act: -0.0000

Data Index: 796392 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1936. Min Act: -0.0000

Data Index: 264555 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1833. Min Act: -0.0000

Data Index: 906911 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2436. Min Act: -0.0000

Data Index: 1237101 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1208330 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.2281. Min Act: -0.0000

Data Index: 662973 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1619. Min Act: -0.0000

Data Index: 743860 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1615. Min Act: -0.0000

Data Index: 1020314 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1660. Min Act: -0.0000

Data Index: 278246 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.1473. Min Act: -0.0000

Data Index: 294031 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.0494. Min Act: -0.0000

Data Index: 338457 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.0767. Min Act: -0.0000

Data Index: 815420 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.0968. Min Act: -0.0000

Data Index: 424628 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.8640. Min Range: -1.8640

Max Act: 1.0772. Min Act: -0.0000

Data Index: 606336 (C4 (Web Text))

Max Activating Token Index: 842