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

Dataset: The Pile

Neuron 397 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: 1.1596. Min Range: -1.1596

Max Act: 1.1478. Min Act: 0.0000

Data Index: 1195153 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0000

Data Index: 667372 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8374. Min Act: -0.0000

Data Index: 270920 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1239829 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1561218 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7917. Min Act: -0.0000

Data Index: 806090 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1814753 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1592070 (The Pile)

Max Activating Token Index: 806

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7940. Min Act: 0.0000

Data Index: 363994 (The Pile)

Max Activating Token Index: 764

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1265709 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7645. Min Act: -0.0000

Data Index: 524236 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1147955 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1566996 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7471. Min Act: -0.0000

Data Index: 913955 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1540552 (The Pile)

Max Activating Token Index: 95

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7752. Min Act: -0.0000

Data Index: 384718 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1197220 (The Pile)

Max Activating Token Index: 845

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7518. Min Act: -0.0000

Data Index: 930566 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1333699 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1315248 (The Pile)

Max Activating Token Index: 209