Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.1643. Min Act: -0.0000

Data Index: 392048 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.2928. Min Act: -0.0000

Data Index: 32628 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.2492. Min Act: -0.0000

Data Index: 170250 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.1592. Min Act: -0.0000

Data Index: 911152 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.1456. Min Act: -0.0000

Data Index: 255414 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9208. Min Act: -0.0000

Data Index: 743164 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0075. Min Act: -0.0000

Data Index: 67310 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0192. Min Act: -0.0000

Data Index: 156713 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.7913. Min Act: -0.0000

Data Index: 603086 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9821. Min Act: -0.0000

Data Index: 571910 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0899. Min Act: -0.0000

Data Index: 366609 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9764. Min Act: -0.0000

Data Index: 384187 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.7761. Min Act: -0.0000

Data Index: 775942 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0631. Min Act: -0.0000

Data Index: 195289 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9621. Min Act: -0.0000

Data Index: 497757 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9584. Min Act: -0.0000

Data Index: 606392 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9086. Min Act: -0.0000

Data Index: 1222185 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.9310. Min Act: -0.0000

Data Index: 1258352 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 2.2928. Min Range: -2.2928

Max Act: 1.8432. Min Act: -0.0000

Data Index: 690481 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.2928. Min Range: -2.2928

Max Act: 2.0437. Min Act: -0.0000

Data Index: 1059582 (C4 (Web Text))

Max Activating Token Index: 153