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

Dataset: The Pile

Neuron 1817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1780000 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1133285 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.6263. Min Act: -0.0000

Data Index: 1074358 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.5705. Min Act: -0.0000

Data Index: 1024583 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1583077 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1691078 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2026. Min Act: -0.0000

Data Index: 700550 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2133. Min Act: -0.0000

Data Index: 309475 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.1184. Min Act: -0.0000

Data Index: 307191 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2595. Min Act: -0.0000

Data Index: 270363 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0459. Min Act: -0.0000

Data Index: 212899 (The Pile)

Max Activating Token Index: 828

Text #11

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0072. Min Act: -0.0000

Data Index: 804950 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1761259 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.2248. Min Act: -0.0000

Data Index: 1130444 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.1617. Min Act: -0.0000

Data Index: 637405 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1755073 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1028607 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1268378 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0382. Min Act: -0.0000

Data Index: 614191 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.6263. Min Range: -1.6263

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1155014 (The Pile)

Max Activating Token Index: 501