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

Dataset: The Pile

Neuron 3617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1250439 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1253552 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7192. Min Act: -0.0000

Data Index: 665492 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7443. Min Act: -0.0001

Data Index: 243608 (The Pile)

Max Activating Token Index: 145

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1115394 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1829880 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1035337 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7323. Min Act: -0.0000

Data Index: 519522 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6767. Min Act: -0.0000

Data Index: 39002 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1852146 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1500521 (The Pile)

Max Activating Token Index: 418

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1982724 (The Pile)

Max Activating Token Index: 424

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6213. Min Act: -0.0000

Data Index: 674980 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1050513 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6918. Min Act: -0.0000

Data Index: 560153 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1837602 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1922208 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6170. Min Act: -0.0000

Data Index: 284762 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4837. Min Act: -0.0000

Data Index: 901848 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1862923 (The Pile)

Max Activating Token Index: 288