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

Dataset: The Pile

Neuron 1848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0287. Min Range: -1.0287

Max Act: 1.0287. Min Act: -0.0000

Data Index: 890097 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9546. Min Act: -0.0000

Data Index: 558420 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8867. Min Act: -0.0000

Data Index: 735268 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.9418. Min Act: -0.0000

Data Index: 452310 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8343. Min Act: -0.0000

Data Index: 191541 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1135370 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8684. Min Act: -0.0000

Data Index: 988789 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1337414 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1300422 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7136. Min Act: -0.0000

Data Index: 84374 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1599571 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6895. Min Act: -0.0000

Data Index: 263455 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1669469 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6428. Min Act: -0.0000

Data Index: 156862 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1747977 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6525. Min Act: -0.0000

Data Index: 782843 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6694. Min Act: -0.0000

Data Index: 298541 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1403974 (The Pile)

Max Activating Token Index: 942

Text #18

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1608445 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 1.0287. Min Range: -1.0287

Max Act: 0.6448. Min Act: -0.0000

Data Index: 500659 (The Pile)

Max Activating Token Index: 922