Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 9 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2926. Min Act: -0.0000

Data Index: 248505 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2851. Min Act: -0.0000

Data Index: 555965 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1878466 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2764. Min Act: -0.0000

Data Index: 635168 (The Pile)

Max Activating Token Index: 411

Text #4

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2813. Min Act: -0.0000

Data Index: 537121 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1300386 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1040419 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1905394 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1424064 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1156598 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2589. Min Act: -0.0000

Data Index: 240338 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2481. Min Act: -0.0001

Data Index: 867773 (The Pile)

Max Activating Token Index: 257

Text #12

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1458621 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1792762 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1555702 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2515. Min Act: -0.0000

Data Index: 174711 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1199549 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2403. Min Act: -0.0000

Data Index: 196673 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1208352 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.2956. Min Range: -0.2956

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1622002 (The Pile)

Max Activating Token Index: 667