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

Dataset: The Pile

Neuron 145 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.7594. Min Act: -0.0000

Data Index: 520928 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1471349 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5269. Min Act: -0.0000

Data Index: 612889 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1500733 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1273923 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5075. Min Act: -0.0000

Data Index: 127543 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4962. Min Act: -0.0000

Data Index: 197014 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5061. Min Act: -0.0000

Data Index: 863384 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4599. Min Act: -0.0000

Data Index: 591214 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5428. Min Act: -0.0000

Data Index: 973654 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5028. Min Act: -0.0000

Data Index: 725052 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4768. Min Act: -0.0000

Data Index: 933315 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1155837 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1782290 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4665. Min Act: -0.0000

Data Index: 138099 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1708132 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.5046. Min Act: -0.0000

Data Index: 188776 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4434. Min Act: 0.0000

Data Index: 1790640 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4450. Min Act: -0.0000

Data Index: 342492 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.7594. Min Range: -0.7594

Max Act: 0.4399. Min Act: -0.0000

Data Index: 817480 (The Pile)

Max Activating Token Index: 222