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

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

Neuron 1343 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.4769. Min Act: -0.0000

Data Index: 176042 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.6262. Min Act: -0.0000

Data Index: 579108 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.5985. Min Act: -0.0000

Data Index: 444473 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1057042 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.3591. Min Act: -0.0000

Data Index: 1149676 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.4351. Min Act: -0.0000

Data Index: 156222 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.3614. Min Act: -0.0000

Data Index: 103001 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.3551. Min Act: -0.0000

Data Index: 1040359 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.3347. Min Act: -0.0000

Data Index: 1045901 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.2717. Min Act: -0.0000

Data Index: 71000 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1607. Min Act: -0.0000

Data Index: 823162 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1505. Min Act: -0.0000

Data Index: 888790 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.2203. Min Act: -0.0000

Data Index: 487977 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.2084. Min Act: -0.0000

Data Index: 643910 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1932. Min Act: -0.0000

Data Index: 925236 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1684. Min Act: -0.0000

Data Index: 651470 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.0629. Min Act: -0.0000

Data Index: 832012 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1723. Min Act: -0.0000

Data Index: 604971 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1736. Min Act: -0.0000

Data Index: 539751 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 2.6262. Min Range: -2.6262

Max Act: 2.1353. Min Act: -0.0000

Data Index: 164174 (C4 (Web Text))

Max Activating Token Index: 563