Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2660 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.9382. Min Act: -0.0000

Data Index: 59174 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.9606. Min Act: -0.0000

Data Index: 1873568 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.4460. Min Act: -0.0000

Data Index: 172502 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.1557. Min Act: -0.0000

Data Index: 12410 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.4268. Min Act: -0.0000

Data Index: 970794 (The Pile)

Max Activating Token Index: 54

Text #5

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.4268. Min Act: -0.0000

Data Index: 1675237 (The Pile)

Max Activating Token Index: 54

Text #6

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.3231. Min Act: -0.0000

Data Index: 502821 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.1550. Min Act: -0.0000

Data Index: 53594 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.9786. Min Act: -0.0000

Data Index: 327405 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.5386. Min Act: -0.0000

Data Index: 535574 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2516. Min Act: -0.0000

Data Index: 787608 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2431. Min Act: -0.0000

Data Index: 1211302 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.3344. Min Act: -0.0000

Data Index: 726742 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1272952 (The Pile)

Max Activating Token Index: 75

Text #14

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.0112. Min Act: -0.0000

Data Index: 254353 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.0529. Min Act: -0.0000

Data Index: 1985060 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.0144. Min Act: -0.0000

Data Index: 8772 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2672. Min Act: -0.0000

Data Index: 1590070 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 3.9606. Min Range: -3.9606

Max Act: 2.9655. Min Act: -0.0000

Data Index: 1157548 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 3.9606. Min Range: -3.9606

Max Act: 3.2655. Min Act: -0.0000

Data Index: 1215314 (The Pile)

Max Activating Token Index: 191