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

Dataset: The Pile

Neuron 4612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7520. Min Act: -0.0000

Data Index: 845350 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7857. Min Act: -0.0000

Data Index: 904183 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7487. Min Act: -0.0000

Data Index: 991125 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1120303 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1398938 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6189. Min Act: -0.0000

Data Index: 925479 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1515300 (The Pile)

Max Activating Token Index: 349

Text #7

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1244063 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6231. Min Act: -0.0000

Data Index: 20984 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5920. Min Act: -0.0000

Data Index: 904886 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1209529 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1738441 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5668. Min Act: -0.0000

Data Index: 490321 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1426801 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1099380 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1243936 (The Pile)

Max Activating Token Index: 723

Text #16

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1373587 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5166. Min Act: -0.0000

Data Index: 560189 (The Pile)

Max Activating Token Index: 702

Text #18

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5338. Min Act: -0.0000

Data Index: 641615 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1248292 (The Pile)

Max Activating Token Index: 922