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

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

Neuron 4928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0489. Min Act: -0.0002

Data Index: 274302 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1007299 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1232843 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0470. Min Act: -0.0002

Data Index: 275137 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1152757 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0438. Min Act: -0.0002

Data Index: 269664 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0470. Min Act: -0.0002

Data Index: 675987 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1245098 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0390. Min Act: -0.0002

Data Index: 121037 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0434. Min Act: -0.0002

Data Index: 611205 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1246464 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0471. Min Act: -0.0002

Data Index: 155132 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1272771 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0371. Min Act: -0.0002

Data Index: 283832 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0314. Min Act: -0.0002

Data Index: 6717 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1253667 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1090432 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1056932 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0463. Min Act: -0.0002

Data Index: 433737 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0412. Min Act: -0.0002

Data Index: 275474 (C4 (Web Text))

Max Activating Token Index: 37