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

Dataset: The Pile

Neuron 845 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: 3.4790. Min Range: -3.4790

Max Act: 3.3828. Min Act: -0.0000

Data Index: 1798693 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.3547. Min Act: -0.0000

Data Index: 987804 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.0352. Min Act: -0.0000

Data Index: 87076 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.4790. Min Act: -0.0000

Data Index: 170550 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.1648. Min Act: -0.0000

Data Index: 433921 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.1443. Min Act: -0.0000

Data Index: 602935 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.9312. Min Act: -0.0000

Data Index: 936036 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.2041. Min Act: -0.0000

Data Index: 1304942 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.2638. Min Act: -0.0000

Data Index: 413343 (The Pile)

Max Activating Token Index: 348

Text #9

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.2248. Min Act: -0.0000

Data Index: 1205919 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.0268. Min Act: -0.0000

Data Index: 1974021 (The Pile)

Max Activating Token Index: 451

Text #11

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.9124. Min Act: -0.0000

Data Index: 1502608 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.1611. Min Act: -0.0000

Data Index: 89197 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.1641. Min Act: -0.0000

Data Index: 1528438 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.0419. Min Act: -0.0000

Data Index: 1475019 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.8578. Min Act: -0.0000

Data Index: 353356 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 3.4790. Min Range: -3.4790

Max Act: 3.1105. Min Act: -0.0000

Data Index: 1408260 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.9326. Min Act: -0.0000

Data Index: 1813889 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.7549. Min Act: -0.0000

Data Index: 609192 (The Pile)

Max Activating Token Index: 239

Text #19

Max Range: 3.4790. Min Range: -3.4790

Max Act: 2.8947. Min Act: -0.0000

Data Index: 209092 (The Pile)

Max Activating Token Index: 1013