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

Dataset: The Pile

Neuron 328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.7467. Min Act: -0.0000

Data Index: 219021 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1448579 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6442. Min Act: -0.0000

Data Index: 433679 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5851. Min Act: -0.0000

Data Index: 612587 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1897821 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1138071 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1364062 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1521656 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5864. Min Act: -0.0000

Data Index: 860016 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5468. Min Act: -0.0000

Data Index: 299568 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5104. Min Act: -0.0000

Data Index: 549047 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1159053 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5346. Min Act: -0.0000

Data Index: 421862 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5045. Min Act: -0.0000

Data Index: 493735 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1651248 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1928143 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5198. Min Act: -0.0000

Data Index: 12723 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.5019. Min Act: -0.0000

Data Index: 267584 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.4818. Min Act: -0.0000

Data Index: 176047 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.7467. Min Range: -0.7467

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1457619 (The Pile)

Max Activating Token Index: 174