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

Dataset: The Pile

Neuron 3772 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: 5.8017. Min Range: -5.8017

Max Act: 5.8017. Min Act: -0.0000

Data Index: 1990931 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 5.8017. Min Range: -5.8017

Max Act: 5.1775. Min Act: -0.0000

Data Index: 1121433 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 5.8017. Min Range: -5.8017

Max Act: 5.2988. Min Act: -0.0000

Data Index: 1273690 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.7868. Min Act: -0.0000

Data Index: 896069 (The Pile)

Max Activating Token Index: 634

Text #4

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.6964. Min Act: -0.0000

Data Index: 967489 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.4800. Min Act: -0.0000

Data Index: 71368 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.2834. Min Act: -0.0000

Data Index: 1904775 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.5439. Min Act: -0.0000

Data Index: 877492 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.3272. Min Act: -0.0000

Data Index: 630620 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.8053. Min Act: -0.0000

Data Index: 1099144 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.1242. Min Act: -0.0000

Data Index: 1627187 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.7504. Min Act: -0.0000

Data Index: 82901 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.7341. Min Act: -0.0000

Data Index: 717839 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.8820. Min Act: -0.0000

Data Index: 275623 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.8142. Min Act: -0.0000

Data Index: 628095 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.8286. Min Act: -0.0000

Data Index: 1548845 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.9500. Min Act: -0.0000

Data Index: 697161 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.0709. Min Act: -0.0000

Data Index: 1543360 (The Pile)

Max Activating Token Index: 741

Text #18

Max Range: 5.8017. Min Range: -5.8017

Max Act: 4.0429. Min Act: -0.0000

Data Index: 757079 (The Pile)

Max Activating Token Index: 182

Text #19

Max Range: 5.8017. Min Range: -5.8017

Max Act: 3.7086. Min Act: -0.0000

Data Index: 1937294 (The Pile)

Max Activating Token Index: 1003