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

Dataset: The Pile

Neuron 2554 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: 0.9065. Min Range: -0.9065

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1204021 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1420318 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1036571 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1312531 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1490131 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8024. Min Act: -0.0000

Data Index: 499759 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8045. Min Act: -0.0000

Data Index: 888468 (The Pile)

Max Activating Token Index: 294

Text #7

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1675804 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1742824 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7931. Min Act: -0.0000

Data Index: 852820 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1828425 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1024 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1314535 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8017. Min Act: -0.0000

Data Index: 447323 (The Pile)

Max Activating Token Index: 291

Text #14

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1549928 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6662. Min Act: -0.0000

Data Index: 91942 (The Pile)

Max Activating Token Index: 124

Text #16

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7347. Min Act: -0.0000

Data Index: 753391 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1284411 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.8029. Min Act: -0.0000

Data Index: 392582 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7686. Min Act: -0.0000

Data Index: 481134 (The Pile)

Max Activating Token Index: 414