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

Dataset: The Pile

Neuron 3101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.4244. Min Act: -0.0000

Data Index: 597448 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.0886. Min Act: -0.0000

Data Index: 784420 (The Pile)

Max Activating Token Index: 954

Text #2

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.4721. Min Act: -0.0000

Data Index: 545946 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.2926. Min Act: -0.0000

Data Index: 113278 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.1598. Min Act: -0.0000

Data Index: 1858244 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.1168. Min Act: -0.0000

Data Index: 1750320 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9322. Min Act: -0.0000

Data Index: 730521 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 3.4721. Min Range: -3.4721

Max Act: 3.0100. Min Act: -0.0000

Data Index: 1763388 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1834841 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9292. Min Act: -0.0000

Data Index: 1677013 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.7514. Min Act: -0.0000

Data Index: 1029126 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8722. Min Act: -0.0000

Data Index: 952260 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8459. Min Act: -0.0000

Data Index: 787126 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.8252. Min Act: -0.0000

Data Index: 881551 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.6744. Min Act: -0.0000

Data Index: 804773 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.9412. Min Act: -0.0000

Data Index: 1514811 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.7660. Min Act: -0.0000

Data Index: 575360 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.7975. Min Act: -0.0000

Data Index: 1765124 (The Pile)

Max Activating Token Index: 876

Text #18

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.6585. Min Act: -0.0000

Data Index: 1081904 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 3.4721. Min Range: -3.4721

Max Act: 2.6457. Min Act: -0.0000

Data Index: 1727677 (The Pile)

Max Activating Token Index: 943