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

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

Neuron 3135 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: 7.0917. Min Range: -7.0917

Max Act: 7.0917. Min Act: -0.0000

Data Index: 69548 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 7.0917. Min Range: -7.0917

Max Act: 6.3509. Min Act: -0.0000

Data Index: 765915 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 7.0917. Min Range: -7.0917

Max Act: 5.7665. Min Act: -0.0000

Data Index: 447866 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 7.0917. Min Range: -7.0917

Max Act: 5.5815. Min Act: -0.0000

Data Index: 118824 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.6763. Min Act: -0.0000

Data Index: 577064 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 7.0917. Min Range: -7.0917

Max Act: 6.3736. Min Act: -0.0000

Data Index: 979658 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 7.0917. Min Range: -7.0917

Max Act: 5.4405. Min Act: -0.0000

Data Index: 997306 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 7.0917. Min Range: -7.0917

Max Act: 3.8938. Min Act: -0.0000

Data Index: 832801 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.7392. Min Act: -0.0000

Data Index: 1126140 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.6355. Min Act: -0.0000

Data Index: 925326 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.7881. Min Act: -0.0000

Data Index: 1232870 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.3347. Min Act: -0.0000

Data Index: 285894 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 7.0917. Min Range: -7.0917

Max Act: 5.8459. Min Act: -0.0000

Data Index: 1255995 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.2836. Min Act: -0.0000

Data Index: 375356 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 7.0917. Min Range: -7.0917

Max Act: 5.2376. Min Act: -0.0000

Data Index: 546681 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.8313. Min Act: -0.0000

Data Index: 1268814 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.0643. Min Act: -0.0000

Data Index: 310897 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 7.0917. Min Range: -7.0917

Max Act: 3.9014. Min Act: -0.0000

Data Index: 1313741 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.0331. Min Act: -0.0000

Data Index: 567361 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 7.0917. Min Range: -7.0917

Max Act: 4.1545. Min Act: -0.0000

Data Index: 1330392 (C4 (Web Text))

Max Activating Token Index: 545