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

Dataset: The Pile

Neuron 1629 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.5288. Min Act: -0.0000

Data Index: 558407 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4597. Min Act: 0.0000

Data Index: 1630907 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4308. Min Act: -0.0000

Data Index: 459231 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1651978 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3777. Min Act: -0.0000

Data Index: 683561 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1101927 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.4336. Min Act: -0.0000

Data Index: 390875 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3562. Min Act: -0.0000

Data Index: 326967 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1968151 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1119725 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1384479 (The Pile)

Max Activating Token Index: 471

Text #11

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3265. Min Act: -0.0000

Data Index: 821757 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1310201 (The Pile)

Max Activating Token Index: 794

Text #13

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3280. Min Act: -0.0000

Data Index: 854178 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1958052 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3272. Min Act: -0.0000

Data Index: 243951 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1196949 (The Pile)

Max Activating Token Index: 725

Text #17

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1469403 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.3239. Min Act: -0.0000

Data Index: 285847 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 0.5288. Min Range: -0.5288

Max Act: 0.2912. Min Act: -0.0000

Data Index: 806821 (The Pile)

Max Activating Token Index: 319