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

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

Neuron 4706 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.8794. Min Act: -0.0000

Data Index: 49633 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.7785. Min Act: -0.0000

Data Index: 516516 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 3.0607. Min Range: -3.0607

Max Act: 3.0607. Min Act: -0.0000

Data Index: 1436405 (Python Code)

Max Activating Token Index: 175

Text #3

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.8734. Min Act: -0.0000

Data Index: 1261855 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.6511. Min Act: -0.0000

Data Index: 1482420 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.7707. Min Act: -0.0000

Data Index: 504714 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.6223. Min Act: -0.0000

Data Index: 138260 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.5809. Min Act: -0.0000

Data Index: 814329 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1383766 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.5202. Min Act: -0.0000

Data Index: 1329994 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.5155. Min Act: -0.0000

Data Index: 1590196 (Python Code)

Max Activating Token Index: 90

Text #11

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.4744. Min Act: -0.0000

Data Index: 315752 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1448731 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.4373. Min Act: -0.0000

Data Index: 1230987 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.3998. Min Act: -0.0000

Data Index: 234006 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.2466. Min Act: -0.0000

Data Index: 1325425 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.1867. Min Act: -0.0000

Data Index: 700405 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.2981. Min Act: -0.0000

Data Index: 228960 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.3119. Min Act: -0.0000

Data Index: 583500 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.0607. Min Range: -3.0607

Max Act: 2.2933. Min Act: -0.0000

Data Index: 1641286 (Python Code)

Max Activating Token Index: 178