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

Dataset: The Pile

Neuron 3025 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9978. Min Act: -0.0000

Data Index: 267301 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.4921. Min Act: -0.0000

Data Index: 461462 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.1820. Min Act: -0.0000

Data Index: 1379257 (The Pile)

Max Activating Token Index: 320

Text #3

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9419. Min Act: -0.0000

Data Index: 973512 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.1865. Min Act: -0.0000

Data Index: 1323735 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9851. Min Act: -0.0000

Data Index: 1761663 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9501. Min Act: -0.0000

Data Index: 257305 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.3210. Min Act: -0.0000

Data Index: 1073529 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.0399. Min Act: -0.0000

Data Index: 668539 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9992. Min Act: -0.0000

Data Index: 1577172 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.7568. Min Act: -0.0000

Data Index: 450848 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9707. Min Act: -0.0000

Data Index: 734266 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.5621. Min Act: -0.0000

Data Index: 890028 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 3.4921. Min Range: -3.4921

Max Act: 3.0315. Min Act: -0.0000

Data Index: 1749787 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9301. Min Act: -0.0000

Data Index: 1221053 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.6770. Min Act: -0.0000

Data Index: 1169140 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9109. Min Act: -0.0000

Data Index: 1172003 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.8833. Min Act: -0.0000

Data Index: 11039 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9794. Min Act: -0.0000

Data Index: 578018 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 3.4921. Min Range: -3.4921

Max Act: 2.9838. Min Act: -0.0000

Data Index: 820844 (The Pile)

Max Activating Token Index: 403