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

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

Neuron 1597 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.9516. Min Act: -0.0000

Data Index: 1362821 (Python Code)

Max Activating Token Index: 786

Text #1

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1483007 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.6214. Min Act: -0.0000

Data Index: 936876 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4315. Min Act: -0.0000

Data Index: 994643 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1027509 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4864. Min Act: -0.0000

Data Index: 222882 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4835. Min Act: -0.0000

Data Index: 268036 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4733. Min Act: -0.0000

Data Index: 437117 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4260. Min Act: -0.0000

Data Index: 1185854 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4020. Min Act: -0.0000

Data Index: 53314 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1576874 (Python Code)

Max Activating Token Index: 49

Text #11

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.3900. Min Act: -0.0000

Data Index: 1249209 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.3714. Min Act: -0.0000

Data Index: 91075 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.3673. Min Act: -0.0000

Data Index: 106714 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.3636. Min Act: -0.0000

Data Index: 385217 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.3621. Min Act: -0.0000

Data Index: 171805 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.2812. Min Act: -0.0000

Data Index: 946337 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.2640. Min Act: -0.0000

Data Index: 201628 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.2515. Min Act: -0.0000

Data Index: 609958 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.9516. Min Range: -1.9516

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1652019 (Python Code)

Max Activating Token Index: 273