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

Dataset: The Pile

Neuron 2066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0000

Data Index: 11725 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4472. Min Act: -0.0000

Data Index: 369828 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3927. Min Act: -0.0000

Data Index: 741738 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1817049 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1221751 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3769. Min Act: -0.0000

Data Index: 249252 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3127. Min Act: -0.0000

Data Index: 604545 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1278454 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3677. Min Act: -0.0000

Data Index: 40722 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1558485 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1386844 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3586. Min Act: -0.0000

Data Index: 774977 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3661. Min Act: -0.0000

Data Index: 669390 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1879264 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3680. Min Act: -0.0000

Data Index: 898674 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1647599 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3184. Min Act: -0.0000

Data Index: 655899 (The Pile)

Max Activating Token Index: 171

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3315. Min Act: -0.0000

Data Index: 435453 (The Pile)

Max Activating Token Index: 50

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3320. Min Act: -0.0000

Data Index: 426358 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1419325 (The Pile)

Max Activating Token Index: 525