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

Dataset: The Pile

Neuron 2400 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.8516. Min Act: -0.0000

Data Index: 280398 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1231982 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6859. Min Act: -0.0000

Data Index: 256379 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.7185. Min Act: -0.0000

Data Index: 723359 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6439. Min Act: -0.0000

Data Index: 965774 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1319686 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6853. Min Act: -0.0000

Data Index: 943703 (The Pile)

Max Activating Token Index: 581

Text #7

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6843. Min Act: -0.0000

Data Index: 949122 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6909. Min Act: -0.0000

Data Index: 858313 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1484043 (The Pile)

Max Activating Token Index: 184

Text #10

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6251. Min Act: -0.0000

Data Index: 219657 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1251573 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6384. Min Act: -0.0000

Data Index: 874328 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6279. Min Act: -0.0000

Data Index: 119559 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6321. Min Act: -0.0000

Data Index: 58104 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1288099 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6199. Min Act: -0.0000

Data Index: 493845 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1799249 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1192776 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 0.8516. Min Range: -0.8516

Max Act: 0.6060. Min Act: -0.0000

Data Index: 325948 (The Pile)

Max Activating Token Index: 30