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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4218 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6745. Min Act: -0.0000

Data Index: 42448 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1125554 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1322337 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.6140. Min Act: -0.0000

Data Index: 683443 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1154354 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5432. Min Act: -0.0000

Data Index: 910049 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4854. Min Act: -0.0000

Data Index: 239340 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5419. Min Act: -0.0000

Data Index: 886543 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5537. Min Act: -0.0000

Data Index: 940446 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5144. Min Act: -0.0000

Data Index: 621357 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5017. Min Act: -0.0000

Data Index: 334912 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1077224 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.5006. Min Act: -0.0000

Data Index: 776516 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4278. Min Act: -0.0000

Data Index: 107943 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1461304 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1626424 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4561. Min Act: -0.0000

Data Index: 466748 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4143. Min Act: -0.0000

Data Index: 537541 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4473. Min Act: -0.0000

Data Index: 526663 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.6745. Min Range: -0.6745

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1087478 (C4 (Web Text))

Max Activating Token Index: 562