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

Dataset: The Pile

Neuron 942 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1439. Min Range: -3.1439

Max Act: 3.1439. Min Act: -0.0000

Data Index: 420650 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.9196. Min Act: -0.0000

Data Index: 1996481 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2724. Min Act: -0.0000

Data Index: 904456 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.5274. Min Act: -0.0000

Data Index: 1899074 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.3712. Min Act: -0.0000

Data Index: 636718 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2016. Min Act: -0.0000

Data Index: 328557 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4132. Min Act: -0.0001

Data Index: 1330356 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.3732. Min Act: -0.0000

Data Index: 500997 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1596317 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.3752. Min Act: -0.0000

Data Index: 243524 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4873. Min Act: -0.0000

Data Index: 1025012 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4445. Min Act: -0.0000

Data Index: 633649 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2167. Min Act: -0.0000

Data Index: 286252 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1802823 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2819. Min Act: -0.0001

Data Index: 1121253 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2751. Min Act: -0.0000

Data Index: 630194 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.4039. Min Act: -0.0000

Data Index: 14878 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.2669. Min Act: -0.0000

Data Index: 785085 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1645. Min Act: -0.0000

Data Index: 1529115 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 3.1439. Min Range: -3.1439

Max Act: 2.1412. Min Act: -0.0000

Data Index: 128295 (The Pile)

Max Activating Token Index: 52