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

Dataset: The Pile

Neuron 253 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: 1.8184. Min Range: -1.8184

Max Act: 1.8184. Min Act: -0.0000

Data Index: 698820 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.6630. Min Act: -0.0000

Data Index: 862196 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.5704. Min Act: -0.0000

Data Index: 461802 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.5272. Min Act: -0.0000

Data Index: 616 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1352962 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1533875 (The Pile)

Max Activating Token Index: 855

Text #6

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1942559 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.4159. Min Act: -0.0000

Data Index: 246028 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1873039 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1391406 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.4441. Min Act: -0.0000

Data Index: 34318 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.5070. Min Act: -0.0000

Data Index: 1653530 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.3371. Min Act: -0.0000

Data Index: 331517 (The Pile)

Max Activating Token Index: 583

Text #13

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.1996. Min Act: -0.0000

Data Index: 533560 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1171658 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1163179 (The Pile)

Max Activating Token Index: 162

Text #16

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.3043. Min Act: -0.0000

Data Index: 781938 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1605076 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.2618. Min Act: -0.0000

Data Index: 1787184 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 1.8184. Min Range: -1.8184

Max Act: 1.1764. Min Act: -0.0000

Data Index: 523598 (The Pile)

Max Activating Token Index: 739