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

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

Neuron 4115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.3150. Min Act: -0.0000

Data Index: 1073648 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.3640. Min Act: -0.0000

Data Index: 842580 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1211878 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1895. Min Act: -0.0000

Data Index: 512235 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.2425. Min Act: -0.0000

Data Index: 587825 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1520. Min Act: -0.0000

Data Index: 871285 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1490. Min Act: -0.0000

Data Index: 560943 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1624. Min Act: -0.0000

Data Index: 889719 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1285545 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1160289 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9617. Min Act: -0.0000

Data Index: 465911 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0111. Min Act: -0.0000

Data Index: 915720 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0331. Min Act: -0.0000

Data Index: 542332 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.3640. Min Range: -1.3640

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1279884 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9664. Min Act: -0.0000

Data Index: 894843 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9687. Min Act: -0.0000

Data Index: 545152 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.9988. Min Act: -0.0000

Data Index: 485529 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1242836 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1021539 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 1.3640. Min Range: -1.3640

Max Act: 0.8849. Min Act: -0.0000

Data Index: 320036 (C4 (Web Text))

Max Activating Token Index: 448