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

Dataset: The Pile

Neuron 4717 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0896. Min Range: -3.0896

Max Act: 3.0238. Min Act: -0.0000

Data Index: 1586660 (The Pile)

Max Activating Token Index: 74

Text #1

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9578. Min Act: -0.0000

Data Index: 340084 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 3.0896. Min Range: -3.0896

Max Act: 3.0896. Min Act: -0.0000

Data Index: 152594 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.9204. Min Act: -0.0000

Data Index: 1677395 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.8857. Min Act: -0.0000

Data Index: 1486191 (The Pile)

Max Activating Token Index: 457

Text #5

Max Range: 3.0896. Min Range: -3.0896

Max Act: 3.0231. Min Act: -0.0000

Data Index: 593457 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.5866. Min Act: -0.0000

Data Index: 1420890 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.5078. Min Act: -0.0000

Data Index: 813963 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.6523. Min Act: -0.0000

Data Index: 981471 (The Pile)

Max Activating Token Index: 248

Text #9

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.5834. Min Act: -0.0000

Data Index: 1808556 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.6834. Min Act: -0.0000

Data Index: 801067 (The Pile)

Max Activating Token Index: 68

Text #11

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.6668. Min Act: -0.0000

Data Index: 1825822 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.5149. Min Act: -0.0000

Data Index: 157153 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.7870. Min Act: -0.0000

Data Index: 1019568 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.3965. Min Act: -0.0000

Data Index: 1026704 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.4753. Min Act: -0.0000

Data Index: 396671 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.4635. Min Act: -0.0000

Data Index: 793026 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.5349. Min Act: -0.0000

Data Index: 1266567 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.3837. Min Act: -0.0000

Data Index: 601089 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.0896. Min Range: -3.0896

Max Act: 2.1626. Min Act: -0.0000

Data Index: 1430564 (The Pile)

Max Activating Token Index: 879