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

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

Neuron 3258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6941. Min Range: -2.6941

Max Act: 2.6941. Min Act: -0.0000

Data Index: 442895 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 2.6941. Min Range: -2.6941

Max Act: 2.4065. Min Act: -0.0001

Data Index: 610863 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 2.6941. Min Range: -2.6941

Max Act: 2.0892. Min Act: -0.0000

Data Index: 524651 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 2.6941. Min Range: -2.6941

Max Act: 2.0632. Min Act: -0.0000

Data Index: 995644 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.9837. Min Act: -0.0001

Data Index: 705757 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.6941. Min Range: -2.6941

Max Act: 2.0560. Min Act: -0.0001

Data Index: 867462 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.8347. Min Act: -0.0000

Data Index: 661416 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.7762. Min Act: -0.0000

Data Index: 1069874 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1034334 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.8223. Min Act: -0.0001

Data Index: 91769 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.5710. Min Act: -0.0001

Data Index: 811628 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.7642. Min Act: -0.0001

Data Index: 17993 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.7542. Min Act: -0.0000

Data Index: 572810 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.6804. Min Act: -0.0000

Data Index: 951023 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1056630 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.6307. Min Act: -0.0000

Data Index: 1282366 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.5580. Min Act: -0.0000

Data Index: 1019186 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.5868. Min Act: -0.0001

Data Index: 1352905 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1312601 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.6941. Min Range: -2.6941

Max Act: 1.4700. Min Act: -0.0000

Data Index: 538863 (C4 (Web Text))

Max Activating Token Index: 545