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

Dataset: The Pile

Neuron 448 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: 1.2468. Min Range: -1.2468

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1292560 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 1.2468. Min Range: -1.2468

Max Act: 1.1177. Min Act: 0.0000

Data Index: 1584711 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.2468. Min Range: -1.2468

Max Act: 1.0800. Min Act: -0.0000

Data Index: 608870 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8702. Min Act: 0.0000

Data Index: 113155 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8939. Min Act: -0.0000

Data Index: 466501 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8776. Min Act: -0.0000

Data Index: 201972 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8901. Min Act: -0.0000

Data Index: 356589 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.9063. Min Act: -0.0000

Data Index: 193185 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1503228 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.9167. Min Act: -0.0000

Data Index: 128647 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.9231. Min Act: 0.0000

Data Index: 297200 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8824. Min Act: -0.0000

Data Index: 538273 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8319. Min Act: -0.0000

Data Index: 799202 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1330992 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1908693 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1041341 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1971800 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8287. Min Act: -0.0000

Data Index: 937592 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.8285. Min Act: -0.0000

Data Index: 159445 (The Pile)

Max Activating Token Index: 429

Text #19

Max Range: 1.2468. Min Range: -1.2468

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1899094 (The Pile)

Max Activating Token Index: 119