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

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

Neuron 2945 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0153. Min Range: -1.0153

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1112676 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1530674 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1487092 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1432380 (Python Code)

Max Activating Token Index: 828

Text #4

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1645006 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1431321 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1600172 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1497065 (Python Code)

Max Activating Token Index: 180

Text #8

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1455184 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1509512 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1467830 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1454843 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1499533 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1547254 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1377170 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1533946 (Python Code)

Max Activating Token Index: 785

Text #16

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1637708 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1648253 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1587228 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 1.0153. Min Range: -1.0153

Max Act: 0.6321. Min Act: -0.0000

Data Index: 88403 (C4 (Web Text))

Max Activating Token Index: 670