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

Dataset: The Pile

Neuron 3437 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: 0.4500. Min Range: -0.4500

Max Act: 0.4500. Min Act: -0.0000

Data Index: 451734 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3756. Min Act: -0.0000

Data Index: 724374 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1550372 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1972584 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3466. Min Act: -0.0000

Data Index: 216948 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1380765 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1136448 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3575. Min Act: -0.0000

Data Index: 977816 (The Pile)

Max Activating Token Index: 992

Text #8

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3434. Min Act: -0.0000

Data Index: 352137 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3485. Min Act: -0.0000

Data Index: 104350 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3297. Min Act: -0.0000

Data Index: 433316 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1991375 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3569. Min Act: -0.0000

Data Index: 570745 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1771691 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3416. Min Act: -0.0000

Data Index: 898822 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3390. Min Act: -0.0000

Data Index: 518516 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3360. Min Act: -0.0000

Data Index: 90947 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1188867 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3342. Min Act: -0.0000

Data Index: 471619 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.4500. Min Range: -0.4500

Max Act: 0.3107. Min Act: -0.0000

Data Index: 811213 (The Pile)

Max Activating Token Index: 725