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

Dataset: The Pile

Neuron 3896 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: 0.0000

Data Index: 1599235 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1511831 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1287890 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0471. Min Act: -0.0000

Data Index: 311441 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0471. Min Act: -0.0000

Data Index: 159196 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1262405 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0451. Min Act: -0.0000

Data Index: 267872 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0468. Min Act: 0.0000

Data Index: 1045143 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0467. Min Act: 0.0000

Data Index: 1870988 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0464. Min Act: -0.0000

Data Index: 430703 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0464. Min Act: 0.0000

Data Index: 527140 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0462. Min Act: -0.0000

Data Index: 565681 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0462. Min Act: 0.0000

Data Index: 1206929 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0461. Min Act: 0.0000

Data Index: 1440607 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0461. Min Act: 0.0000

Data Index: 1178389 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0442. Min Act: 0.0000

Data Index: 368493 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0458. Min Act: 0.0000

Data Index: 869874 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0458. Min Act: 0.0000

Data Index: 1400783 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0458. Min Act: -0.0000

Data Index: 626374 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0457. Min Act: 0.0000

Data Index: 1467860 (The Pile)

Max Activating Token Index: 1023