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

Dataset: The Pile

Neuron 791 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: 1.6487. Min Range: -1.6487

Max Act: 1.6487. Min Act: -0.0000

Data Index: 1816958 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.4841. Min Act: -0.0000

Data Index: 1181211 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.5207. Min Act: -0.0000

Data Index: 508037 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.4142. Min Act: -0.0000

Data Index: 1354716 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3350. Min Act: -0.0000

Data Index: 132228 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1469818 (The Pile)

Max Activating Token Index: 39

Text #6

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3369. Min Act: -0.0000

Data Index: 84265 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3390. Min Act: -0.0000

Data Index: 130462 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3628. Min Act: -0.0000

Data Index: 993777 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3115. Min Act: -0.0000

Data Index: 582945 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.1908. Min Act: -0.0000

Data Index: 740411 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1235106 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1531112 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1983047 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1437469 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1322523 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2921. Min Act: -0.0000

Data Index: 683243 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2121. Min Act: -0.0000

Data Index: 898715 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1023886 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 1.6487. Min Range: -1.6487

Max Act: 1.1660. Min Act: -0.0000

Data Index: 155512 (The Pile)

Max Activating Token Index: 763