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

Dataset: The Pile

Neuron 2598 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: 1.2057. Min Range: -1.2057

Max Act: 1.2057. Min Act: -0.0000

Data Index: 861245 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.1749. Min Act: -0.0000

Data Index: 245362 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0285. Min Act: -0.0000

Data Index: 529113 (The Pile)

Max Activating Token Index: 549

Text #3

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1866724 (The Pile)

Max Activating Token Index: 445

Text #4

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1633788 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9515. Min Act: -0.0000

Data Index: 941318 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1098540 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1582751 (The Pile)

Max Activating Token Index: 768

Text #8

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9477. Min Act: -0.0000

Data Index: 588818 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9321. Min Act: -0.0000

Data Index: 564225 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1600704 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 1.2057. Min Range: -1.2057

Max Act: 1.0189. Min Act: -0.0000

Data Index: 646656 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1905363 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8459. Min Act: -0.0000

Data Index: 79283 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1914517 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8602. Min Act: -0.0001

Data Index: 1866052 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1200849 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7777. Min Act: -0.0000

Data Index: 235230 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.8088. Min Act: -0.0001

Data Index: 1917856 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 1.2057. Min Range: -1.2057

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1609203 (The Pile)

Max Activating Token Index: 193