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

Dataset: The Pile

Neuron 1585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9980. Min Act: -0.0000

Data Index: 288754 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1003977 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8213. Min Act: -0.0000

Data Index: 580780 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1138738 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1693081 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7756. Min Act: -0.0000

Data Index: 656943 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1179180 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6715. Min Act: -0.0000

Data Index: 49717 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1753543 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1571365 (The Pile)

Max Activating Token Index: 221

Text #10

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1532326 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7093. Min Act: -0.0000

Data Index: 269915 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6854. Min Act: -0.0000

Data Index: 268983 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6838. Min Act: -0.0000

Data Index: 622857 (The Pile)

Max Activating Token Index: 305

Text #14

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1285157 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1299121 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1872711 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6629. Min Act: -0.0000

Data Index: 512560 (The Pile)

Max Activating Token Index: 202

Text #18

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6434. Min Act: -0.0000

Data Index: 141620 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.6660. Min Act: -0.0000

Data Index: 714856 (The Pile)

Max Activating Token Index: 236