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

Dataset: The Pile

Neuron 4945 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: 1.5517. Min Range: -1.5517

Max Act: 1.5517. Min Act: -0.0000

Data Index: 823186 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1141864 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.3767. Min Act: -0.0000

Data Index: 69897 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1751. Min Act: -0.0000

Data Index: 805784 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1790165 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1530329 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1075. Min Act: -0.0000

Data Index: 6233 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1765534 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1851715 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0426. Min Act: -0.0000

Data Index: 558635 (The Pile)

Max Activating Token Index: 49

Text #10

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1265142 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0359. Min Act: -0.0000

Data Index: 284191 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.1306. Min Act: -0.0000

Data Index: 396008 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1602128 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 1.5517. Min Range: -1.5517

Max Act: 1.0452. Min Act: -0.0000

Data Index: 1219204 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9348. Min Act: -0.0000

Data Index: 712900 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1388021 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9890. Min Act: -0.0000

Data Index: 862887 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9114. Min Act: -0.0000

Data Index: 663688 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 1.5517. Min Range: -1.5517

Max Act: 0.9469. Min Act: -0.0000

Data Index: 715493 (The Pile)

Max Activating Token Index: 935