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

Dataset: The Pile

Neuron 1899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1949971 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7558. Min Act: -0.0000

Data Index: 611489 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1591397 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1866123 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1409008 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6995. Min Act: -0.0000

Data Index: 275603 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.7793. Min Act: -0.0000

Data Index: 527333 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1585334 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6542. Min Act: -0.0000

Data Index: 195740 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6572. Min Act: -0.0000

Data Index: 585890 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1416450 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.5661. Min Act: -0.0000

Data Index: 306527 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1334266 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1459666 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1144598 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1403616 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6925. Min Act: -0.0000

Data Index: 482336 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1581248 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.4624. Min Act: -0.0000

Data Index: 794361 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.7886. Min Range: -0.7886

Max Act: 0.6014. Min Act: -0.0000

Data Index: 145211 (The Pile)

Max Activating Token Index: 260