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

Dataset: The Pile

Neuron 3752 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: 0.9776. Min Range: -0.9776

Max Act: 0.9512. Min Act: -0.0000

Data Index: 916457 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.9776. Min Act: -0.0000

Data Index: 299652 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1612277 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7864. Min Act: -0.0000

Data Index: 574935 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1582244 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8317. Min Act: -0.0000

Data Index: 413435 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1324443 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7524. Min Act: -0.0000

Data Index: 202195 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6623. Min Act: -0.0000

Data Index: 478346 (The Pile)

Max Activating Token Index: 100

Text #9

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1504226 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6327. Min Act: -0.0000

Data Index: 212541 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1365329 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1176441 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1718246 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1161292 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6881. Min Act: -0.0000

Data Index: 992057 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7449. Min Act: -0.0000

Data Index: 838927 (The Pile)

Max Activating Token Index: 863

Text #17

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1462727 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1724537 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.9776. Min Range: -0.9776

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1692695 (The Pile)

Max Activating Token Index: 292