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

Dataset: The Pile

Neuron 3509 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: 1.2850. Min Range: -1.2850

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1875640 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1425164 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1291986 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.1311. Min Act: -0.0000

Data Index: 169663 (The Pile)

Max Activating Token Index: 212

Text #4

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1902934 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0150. Min Act: -0.0000

Data Index: 870297 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9881. Min Act: -0.0000

Data Index: 247873 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1629348 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9903. Min Act: -0.0000

Data Index: 116499 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9737. Min Act: -0.0000

Data Index: 1234873 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.2850. Min Range: -1.2850

Max Act: 1.0450. Min Act: 0.0000

Data Index: 1604178 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9388. Min Act: -0.0000

Data Index: 748095 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9215. Min Act: -0.0000

Data Index: 781075 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1649304 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9604. Min Act: -0.0000

Data Index: 283983 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1078999 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1061435 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.9418. Min Act: -0.0000

Data Index: 313297 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8575. Min Act: -0.0000

Data Index: 35832 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 1.2850. Min Range: -1.2850

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1652637 (The Pile)

Max Activating Token Index: 1016