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

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

Neuron 935 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: 2.5733. Min Range: -2.5733

Max Act: 2.5733. Min Act: -0.0000

Data Index: 1408310 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.5253. Min Act: -0.0001

Data Index: 1514277 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.5235. Min Act: -0.0000

Data Index: 1415129 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.5014. Min Act: -0.0000

Data Index: 1405129 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.4434. Min Act: -0.0000

Data Index: 1502445 (Python Code)

Max Activating Token Index: 482

Text #5

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.4311. Min Act: -0.0000

Data Index: 1388448 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3980. Min Act: -0.0000

Data Index: 1364627 (Python Code)

Max Activating Token Index: 333

Text #7

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3800. Min Act: -0.0000

Data Index: 1537935 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.2670. Min Act: -0.0000

Data Index: 1569957 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1444086 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.2595. Min Act: -0.0000

Data Index: 1452378 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3625. Min Act: -0.0000

Data Index: 1363998 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1528362 (Python Code)

Max Activating Token Index: 384

Text #13

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3221. Min Act: -0.0000

Data Index: 1445546 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1372788 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.1881. Min Act: -0.0000

Data Index: 1604647 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3061. Min Act: -0.0000

Data Index: 1509635 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.3036. Min Act: -0.0000

Data Index: 1386536 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.2950. Min Act: -0.0000

Data Index: 1607384 (Python Code)

Max Activating Token Index: 414

Text #19

Max Range: 2.5733. Min Range: -2.5733

Max Act: 2.2991. Min Act: -0.0000

Data Index: 1604028 (Python Code)

Max Activating Token Index: 127