Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1874 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.9513. Min Act: -0.0000

Data Index: 164054 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1579876 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7582. Min Act: -0.0000

Data Index: 296042 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7706. Min Act: -0.0000

Data Index: 354777 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7387. Min Act: -0.0000

Data Index: 231179 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1849032 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7121. Min Act: -0.0000

Data Index: 948401 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7258. Min Act: -0.0000

Data Index: 205863 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1958318 (The Pile)

Max Activating Token Index: 674

Text #9

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1317607 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7319. Min Act: -0.0000

Data Index: 8459 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7007. Min Act: -0.0000

Data Index: 640196 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1873630 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1624527 (The Pile)

Max Activating Token Index: 592

Text #14

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1204644 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1598677 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6368. Min Act: -0.0000

Data Index: 140973 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1527295 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1369474 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.9513. Min Range: -0.9513

Max Act: 0.6794. Min Act: -0.0001

Data Index: 615635 (The Pile)

Max Activating Token Index: 862