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

Dataset: The Pile

Neuron 4228 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1904549 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1633526 (The Pile)

Max Activating Token Index: 649

Text #2

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3237. Min Act: -0.0000

Data Index: 663177 (The Pile)

Max Activating Token Index: 1019

Text #3

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1602092 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3894. Min Act: -0.0000

Data Index: 711530 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1867415 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.3299. Min Act: -0.0000

Data Index: 1622670 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.4819. Min Act: -0.0000

Data Index: 1399954 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1689866 (The Pile)

Max Activating Token Index: 781

Text #9

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1263216 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1957372 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.1439. Min Act: -0.0000

Data Index: 468761 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1420466 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1485543 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1066794 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1006959 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.5252. Min Range: -1.5252

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1670043 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9164. Min Act: -0.0000

Data Index: 914068 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1781925 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 1.5252. Min Range: -1.5252

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1642870 (The Pile)

Max Activating Token Index: 158