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

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

Neuron 445 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: 5.2281. Min Range: -5.2281

Max Act: 5.2281. Min Act: -0.0000

Data Index: 548479 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 5.2281. Min Range: -5.2281

Max Act: 5.1168. Min Act: -0.0000

Data Index: 1038951 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.8009. Min Act: -0.0000

Data Index: 89447 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.7934. Min Act: -0.0000

Data Index: 512270 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 5.2281. Min Range: -5.2281

Max Act: 5.1688. Min Act: -0.0000

Data Index: 981317 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 5.2281. Min Range: -5.2281

Max Act: 5.1903. Min Act: -0.0000

Data Index: 1106931 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.7592. Min Act: -0.0000

Data Index: 526952 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.0530. Min Act: -0.0000

Data Index: 19097 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.6731. Min Act: -0.0000

Data Index: 986317 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.5120. Min Act: -0.0000

Data Index: 633010 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.0426. Min Act: -0.0000

Data Index: 1124022 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.5449. Min Act: -0.0000

Data Index: 961383 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.1555. Min Act: -0.0000

Data Index: 512464 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.8809. Min Act: -0.0000

Data Index: 1011180 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.1378. Min Act: -0.0000

Data Index: 194118 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.1808. Min Act: -0.0000

Data Index: 597056 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 5.2281. Min Range: -5.2281

Max Act: 3.8046. Min Act: -0.0000

Data Index: 101895 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 5.2281. Min Range: -5.2281

Max Act: 3.6264. Min Act: -0.0000

Data Index: 1226327 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.0851. Min Act: -0.0000

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 5.2281. Min Range: -5.2281

Max Act: 4.0968. Min Act: -0.0000

Data Index: 886814 (C4 (Web Text))

Max Activating Token Index: 1002