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

Dataset: The Pile

Neuron 2751 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: 1.8491. Min Range: -1.8491

Max Act: 1.8491. Min Act: -0.0000

Data Index: 783944 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.6942. Min Act: -0.0000

Data Index: 1525736 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.7240. Min Act: -0.0000

Data Index: 421319 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.6197. Min Act: -0.0000

Data Index: 338516 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5792. Min Act: -0.0000

Data Index: 799233 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5553. Min Act: -0.0000

Data Index: 156070 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1251640 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4291. Min Act: -0.0000

Data Index: 1277855 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5077. Min Act: -0.0000

Data Index: 538541 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4764. Min Act: -0.0000

Data Index: 869955 (The Pile)

Max Activating Token Index: 969

Text #10

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4773. Min Act: -0.0000

Data Index: 806774 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5554. Min Act: -0.0000

Data Index: 340286 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1398398 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1141725 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.3669. Min Act: -0.0000

Data Index: 106000 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4559. Min Act: -0.0000

Data Index: 323239 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5198. Min Act: -0.0000

Data Index: 203835 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1065560 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.3491. Min Act: -0.0000

Data Index: 429954 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 1.8491. Min Range: -1.8491

Max Act: 1.5039. Min Act: -0.0000

Data Index: 715418 (The Pile)

Max Activating Token Index: 218