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

Dataset: The Pile

Neuron 910 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: 0.9384. Min Range: -0.9384

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1166186 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.9287. Min Act: -0.0000

Data Index: 248813 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1674895 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1161765 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1937591 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7634. Min Act: -0.0000

Data Index: 820639 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7484. Min Act: -0.0000

Data Index: 558092 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1623055 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6814. Min Act: -0.0000

Data Index: 481317 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6990. Min Act: -0.0000

Data Index: 999089 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7455. Min Act: -0.0000

Data Index: 378502 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1027505 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7034. Min Act: -0.0000

Data Index: 699971 (The Pile)

Max Activating Token Index: 313

Text #13

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7248. Min Act: -0.0000

Data Index: 685752 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1599131 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6994. Min Act: -0.0000

Data Index: 894037 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1721941 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.7176. Min Act: -0.0000

Data Index: 571056 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6914. Min Act: -0.0000

Data Index: 275168 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.9384. Min Range: -0.9384

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1891596 (The Pile)

Max Activating Token Index: 274