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

Dataset: The Pile

Neuron 3891 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: 1.7032. Min Range: -1.7032

Max Act: 1.7032. Min Act: -0.0000

Data Index: 1202008 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.6361. Min Act: -0.0000

Data Index: 998890 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.6568. Min Act: -0.0000

Data Index: 672789 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.4530. Min Act: -0.0000

Data Index: 958039 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1640898 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.5432. Min Act: -0.0000

Data Index: 934844 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3618. Min Act: -0.0000

Data Index: 263930 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3273. Min Act: -0.0000

Data Index: 706800 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.4050. Min Act: -0.0000

Data Index: 851904 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.2927. Min Act: -0.0000

Data Index: 444929 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3511. Min Act: -0.0000

Data Index: 467175 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1656671 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1478584 (The Pile)

Max Activating Token Index: 370

Text #13

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3243. Min Act: -0.0000

Data Index: 428444 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1008393 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1676651 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.1623. Min Act: -0.0000

Data Index: 497396 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.2991. Min Act: -0.0000

Data Index: 1506685 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.3034. Min Act: -0.0000

Data Index: 1009003 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.7032. Min Range: -1.7032

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1408293 (The Pile)

Max Activating Token Index: 537