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

Dataset: The Pile

Neuron 2117 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: 16.2306. Min Range: -16.2306

Max Act: 15.5528. Min Act: -0.0000

Data Index: 1206801 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 16.2306. Min Range: -16.2306

Max Act: 16.2306. Min Act: -0.0000

Data Index: 1233452 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 16.2306. Min Range: -16.2306

Max Act: 1.7159. Min Act: -0.0000

Data Index: 1485743 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 16.2306. Min Range: -16.2306

Max Act: 13.5800. Min Act: 0.0000

Data Index: 22375 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 16.2306. Min Range: -16.2306

Max Act: 14.9157. Min Act: -0.0000

Data Index: 42437 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 16.2306. Min Range: -16.2306

Max Act: 7.2251. Min Act: -0.0000

Data Index: 66771 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 16.2306. Min Range: -16.2306

Max Act: 13.4526. Min Act: -0.0000

Data Index: 695179 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 16.2306. Min Range: -16.2306

Max Act: 12.8800. Min Act: -0.0000

Data Index: 741577 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 16.2306. Min Range: -16.2306

Max Act: 12.1588. Min Act: -0.0000

Data Index: 1356379 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 16.2306. Min Range: -16.2306

Max Act: 10.8249. Min Act: -0.0000

Data Index: 1239723 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 16.2306. Min Range: -16.2306

Max Act: 10.9062. Min Act: -0.0000

Data Index: 1939417 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 16.2306. Min Range: -16.2306

Max Act: 11.8647. Min Act: -0.0000

Data Index: 205118 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 16.2306. Min Range: -16.2306

Max Act: 10.7328. Min Act: -0.0000

Data Index: 762437 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 16.2306. Min Range: -16.2306

Max Act: 12.1819. Min Act: -0.0000

Data Index: 8112 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 16.2306. Min Range: -16.2306

Max Act: 13.3122. Min Act: 0.0000

Data Index: 174910 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 16.2306. Min Range: -16.2306

Max Act: 12.2799. Min Act: -0.0000

Data Index: 1942103 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 16.2306. Min Range: -16.2306

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1817031 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 16.2306. Min Range: -16.2306

Max Act: 0.0035. Min Act: -0.0000

Data Index: 1267658 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 16.2306. Min Range: -16.2306

Max Act: 7.5348. Min Act: -0.0000

Data Index: 397587 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 16.2306. Min Range: -16.2306

Max Act: 10.5440. Min Act: -0.0000

Data Index: 1826098 (The Pile)

Max Activating Token Index: 457