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

Dataset: The Pile

Neuron 5053 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: 3.1906. Min Range: -3.1906

Max Act: 3.1906. Min Act: -0.0000

Data Index: 1841342 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0557. Min Act: -0.0000

Data Index: 401456 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0335. Min Act: -0.0000

Data Index: 1473498 (The Pile)

Max Activating Token Index: 18

Text #3

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0403. Min Act: -0.0000

Data Index: 796976 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0967. Min Act: -0.0000

Data Index: 1653541 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0741. Min Act: -0.0000

Data Index: 650676 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9311. Min Act: -0.0000

Data Index: 1363009 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9267. Min Act: -0.0000

Data Index: 1689531 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.8940. Min Act: -0.0000

Data Index: 938403 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.8958. Min Act: -0.0000

Data Index: 226782 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0471. Min Act: -0.0000

Data Index: 860966 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9966. Min Act: -0.0000

Data Index: 1671969 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.1495. Min Act: -0.0000

Data Index: 21138 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.8400. Min Act: -0.0000

Data Index: 178350 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9577. Min Act: -0.0000

Data Index: 780992 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.8100. Min Act: -0.0000

Data Index: 471877 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9525. Min Act: -0.0000

Data Index: 1891347 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.9485. Min Act: -0.0000

Data Index: 836164 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 3.1906. Min Range: -3.1906

Max Act: 2.7711. Min Act: -0.0000

Data Index: 45104 (The Pile)

Max Activating Token Index: 24

Text #19

Max Range: 3.1906. Min Range: -3.1906

Max Act: 3.0632. Min Act: -0.0000

Data Index: 922995 (The Pile)

Max Activating Token Index: 652