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

Dataset: The Pile

Neuron 1281 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.8531. Min Act: -0.0000

Data Index: 1606467 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.4941. Min Act: -0.0000

Data Index: 777481 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.3432. Min Act: -0.0000

Data Index: 670945 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1144019 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.2560. Min Act: -0.0000

Data Index: 794928 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 1.8531. Min Range: -1.8531

Max Act: 1.0038. Min Act: -0.0000

Data Index: 805335 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9289. Min Act: -0.0000

Data Index: 218450 (The Pile)

Max Activating Token Index: 330

Text #7

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9490. Min Act: -0.0000

Data Index: 913120 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9847. Min Act: -0.0000

Data Index: 175039 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1814717 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1254809 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9439. Min Act: 0.0000

Data Index: 1251790 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1810850 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9027. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 58

Text #14

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.7459. Min Act: -0.0000

Data Index: 201400 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1402743 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1531318 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1150296 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1377031 (The Pile)

Max Activating Token Index: 125

Text #19

Max Range: 1.8531. Min Range: -1.8531

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1637831 (The Pile)

Max Activating Token Index: 458