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

Dataset: The Pile

Neuron 3028 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: 0.9691. Min Range: -0.9691

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1253934 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.9105. Min Act: -0.0000

Data Index: 153576 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1920464 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1929861 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.9168. Min Act: -0.0000

Data Index: 241033 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8166. Min Act: -0.0000

Data Index: 510670 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8493. Min Act: -0.0000

Data Index: 742260 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8311. Min Act: -0.0000

Data Index: 659274 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1674975 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1949577 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7829. Min Act: -0.0000

Data Index: 606499 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8059. Min Act: -0.0000

Data Index: 177216 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8201. Min Act: -0.0000

Data Index: 1258666 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7991. Min Act: -0.0000

Data Index: 782865 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7931. Min Act: -0.0000

Data Index: 923135 (The Pile)

Max Activating Token Index: 41

Text #15

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1805358 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.6786. Min Act: -0.0000

Data Index: 90470 (The Pile)

Max Activating Token Index: 976

Text #17

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.8251. Min Act: -0.0000

Data Index: 371172 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7674. Min Act: -0.0000

Data Index: 390036 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.9691. Min Range: -0.9691

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1202104 (The Pile)

Max Activating Token Index: 83