Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3420 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1631797 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1609584 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8090. Min Act: -0.0000

Data Index: 390662 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1447394 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1672355 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7997. Min Act: -0.0000

Data Index: 773527 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7478. Min Act: -0.0000

Data Index: 124126 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1448058 (The Pile)

Max Activating Token Index: 683

Text #8

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1948444 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1219940 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7439. Min Act: -0.0000

Data Index: 108011 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1543679 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6728. Min Act: -0.0000

Data Index: 363563 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1599415 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1851048 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6455. Min Act: -0.0000

Data Index: 779241 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1983260 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1094283 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1729482 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.8308. Min Range: -0.8308

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1676096 (The Pile)

Max Activating Token Index: 295