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

Dataset: The Pile

Neuron 2972 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.1244. Min Act: -0.0000

Data Index: 7034 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.1009. Min Act: 0.0000

Data Index: 825521 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.1031. Min Act: -0.0000

Data Index: 699443 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1794945 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9278. Min Act: 0.0000

Data Index: 76164 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1866450 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9076. Min Act: -0.0000

Data Index: 1409108 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8888. Min Act: 0.0001

Data Index: 1181517 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9391. Min Act: -0.0000

Data Index: 762651 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8220. Min Act: 0.0000

Data Index: 196154 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1341547 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8721. Min Act: -0.0000

Data Index: 149402 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8111. Min Act: 0.0000

Data Index: 1747114 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8434. Min Act: -0.0000

Data Index: 655795 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8945. Min Act: -0.0000

Data Index: 1622320 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8491. Min Act: 0.0000

Data Index: 948174 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8489. Min Act: -0.0000

Data Index: 422110 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1484998 (The Pile)

Max Activating Token Index: 319

Text #18

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1727890 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8230. Min Act: -0.0000

Data Index: 534964 (The Pile)

Max Activating Token Index: 400