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

Dataset: The Pile

Neuron 285 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: 1.6115. Min Range: -1.6115

Max Act: 1.5359. Min Act: -0.0000

Data Index: 457460 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1199053 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1402953 (The Pile)

Max Activating Token Index: 408

Text #3

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1910538 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.3080. Min Act: -0.0000

Data Index: 439153 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1223253 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1594. Min Act: -0.0000

Data Index: 317625 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1911386 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1730. Min Act: -0.0000

Data Index: 498771 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1825. Min Act: -0.0000

Data Index: 1024604 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1359. Min Act: -0.0000

Data Index: 371421 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1316. Min Act: -0.0000

Data Index: 911944 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1496. Min Act: -0.0000

Data Index: 895328 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1025918 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.1359. Min Act: -0.0000

Data Index: 293776 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1983819 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0965. Min Act: -0.0000

Data Index: 454661 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0947. Min Act: -0.0000

Data Index: 849503 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0866. Min Act: -0.0000

Data Index: 945153 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 1.6115. Min Range: -1.6115

Max Act: 1.0249. Min Act: -0.0000

Data Index: 534707 (The Pile)

Max Activating Token Index: 729