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

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

Neuron 5877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.6744. Min Act: -0.0002

Data Index: 800159 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.5209. Min Act: -0.0002

Data Index: 597239 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.4276. Min Act: -0.0002

Data Index: 414314 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.4419. Min Act: -0.0002

Data Index: 1042339 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3872. Min Act: -0.0002

Data Index: 438399 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3663. Min Act: -0.0002

Data Index: 887512 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3450. Min Act: -0.0002

Data Index: 1025041 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3581. Min Act: -0.0002

Data Index: 1265628 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3502. Min Act: -0.0002

Data Index: 1010029 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3003. Min Act: -0.0002

Data Index: 743118 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2827. Min Act: -0.0002

Data Index: 1202379 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2447. Min Act: -0.0002

Data Index: 33379 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.3254. Min Act: -0.0002

Data Index: 1100272 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2308. Min Act: -0.0002

Data Index: 870275 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2635. Min Act: -0.0002

Data Index: 276814 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2464. Min Act: -0.0002

Data Index: 1128305 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2700. Min Act: -0.0002

Data Index: 1323698 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.2363. Min Act: -0.0002

Data Index: 943179 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.1774. Min Act: -0.0002

Data Index: 1327481 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.6744. Min Range: -1.6744

Max Act: 1.1873. Min Act: -0.0002

Data Index: 801143 (C4 (Web Text))

Max Activating Token Index: 113