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

Dataset: The Pile

Neuron 2185 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: 7.1448. Min Range: -7.1448

Max Act: 7.1448. Min Act: -0.0000

Data Index: 1847465 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.7656. Min Act: -0.0000

Data Index: 119584 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.2487. Min Act: -0.0000

Data Index: 1834553 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6054. Min Act: -0.0000

Data Index: 1728622 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.7657. Min Act: -0.0000

Data Index: 1226489 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.3567. Min Act: -0.0000

Data Index: 252903 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6991. Min Act: -0.0000

Data Index: 51011 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.7070. Min Act: -0.0000

Data Index: 1513109 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.4786. Min Act: -0.0000

Data Index: 609108 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6559. Min Act: -0.0000

Data Index: 105804 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.4479. Min Act: -0.0000

Data Index: 1558785 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6362. Min Act: -0.0000

Data Index: 1955873 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6229. Min Act: -0.0000

Data Index: 1043081 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6140. Min Act: -0.0000

Data Index: 261429 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6168. Min Act: -0.0000

Data Index: 1855466 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.6062. Min Act: -0.0000

Data Index: 602925 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.5700. Min Act: -0.0000

Data Index: 1851371 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.3926. Min Act: -0.0000

Data Index: 730202 (The Pile)

Max Activating Token Index: 494

Text #18

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.4078. Min Act: -0.0000

Data Index: 1658028 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 7.1448. Min Range: -7.1448

Max Act: 6.5614. Min Act: -0.0000

Data Index: 1734583 (The Pile)

Max Activating Token Index: 318