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

Dataset: The Pile

Neuron 2074 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1848681 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.7414. Min Act: -0.0000

Data Index: 98733 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1883644 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1659928 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3745. Min Act: -0.0000

Data Index: 880164 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.6971. Min Act: -0.0000

Data Index: 1069686 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3385. Min Act: -0.0000

Data Index: 676745 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.4044. Min Act: -0.0000

Data Index: 1147911 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3962. Min Act: -0.0000

Data Index: 1520569 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1726626 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1872130 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1684861 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1040505 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1536669 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3561. Min Act: -0.0000

Data Index: 600024 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.2547. Min Act: -0.0000

Data Index: 270142 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1270792 (The Pile)

Max Activating Token Index: 378

Text #17

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1948266 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1770353 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 1.7982. Min Range: -1.7982

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1472259 (The Pile)

Max Activating Token Index: 621