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

Dataset: The Pile

Neuron 572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2923. Min Act: -0.0000

Data Index: 16756 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1906131 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2616. Min Act: -0.0000

Data Index: 482960 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1734928 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2550. Min Act: -0.0000

Data Index: 526186 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2546. Min Act: -0.0000

Data Index: 930530 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1087308 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2572. Min Act: -0.0000

Data Index: 946365 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1969755 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1440907 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1685343 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2460. Min Act: -0.0000

Data Index: 184435 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1640400 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1627279 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2362. Min Act: -0.0000

Data Index: 246937 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2512. Min Act: -0.0000

Data Index: 688547 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2443. Min Act: -0.0000

Data Index: 708952 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2268. Min Act: -0.0000

Data Index: 438565 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1129373 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.2976. Min Range: -0.2976

Max Act: 0.2494. Min Act: -0.0000

Data Index: 524106 (The Pile)

Max Activating Token Index: 321