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

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

Neuron 395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4571. Min Range: -2.4571

Max Act: 2.4571. Min Act: -0.0000

Data Index: 748119 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.8738. Min Act: -0.0000

Data Index: 1140905 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.7826. Min Act: -0.0000

Data Index: 622020 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.8467. Min Act: -0.0000

Data Index: 107874 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.8672. Min Act: -0.0000

Data Index: 1423115 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.9101. Min Act: -0.0000

Data Index: 1421235 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.8987. Min Act: -0.0000

Data Index: 21341 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.8874. Min Act: -0.0000

Data Index: 1623328 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.7804. Min Act: -0.0000

Data Index: 1600460 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.7734. Min Act: -0.0001

Data Index: 519192 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.7674. Min Act: -0.0000

Data Index: 1400237 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.6498. Min Act: -0.0000

Data Index: 1362256 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.7866. Min Act: -0.0000

Data Index: 1544298 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.6077. Min Act: -0.0000

Data Index: 424467 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.6501. Min Act: -0.0000

Data Index: 1564425 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.4223. Min Act: -0.0000

Data Index: 1585791 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.6993. Min Act: -0.0000

Data Index: 1643312 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1498654 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1610756 (Python Code)

Max Activating Token Index: 336

Text #19

Max Range: 2.4571. Min Range: -2.4571

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1647708 (Python Code)

Max Activating Token Index: 181