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

Dataset: The Pile

Neuron 3174 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.6768. Min Act: -0.0000

Data Index: 492076 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.5685. Min Act: -0.0000

Data Index: 142576 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.5606. Min Act: -0.0000

Data Index: 734361 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.4756. Min Act: -0.0000

Data Index: 189819 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.5129. Min Act: -0.0000

Data Index: 355291 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1752573 (The Pile)

Max Activating Token Index: 924

Text #6

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.4604. Min Act: -0.0000

Data Index: 1204205 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.4324. Min Act: -0.0000

Data Index: 862968 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.3416. Min Act: -0.0000

Data Index: 545559 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2421. Min Act: -0.0000

Data Index: 598429 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2455. Min Act: -0.0000

Data Index: 941981 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1755393 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2079. Min Act: -0.0000

Data Index: 920101 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1188226 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2011. Min Act: -0.0000

Data Index: 909913 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.3443. Min Act: -0.0000

Data Index: 1459376 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2684. Min Act: -0.0000

Data Index: 20514 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.3502. Min Act: -0.0000

Data Index: 585439 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.1841. Min Act: -0.0000

Data Index: 123866 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 1.6768. Min Range: -1.6768

Max Act: 1.2496. Min Act: -0.0000

Data Index: 1365662 (The Pile)

Max Activating Token Index: 358