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

Dataset: The Pile

Neuron 3443 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1933. Min Range: -3.1933

Max Act: 3.1933. Min Act: -0.0000

Data Index: 1310575 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.9622. Min Act: -0.0000

Data Index: 637492 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1790512 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1405821 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.6313. Min Act: -0.0000

Data Index: 495327 (The Pile)

Max Activating Token Index: 537

Text #5

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.5483. Min Act: -0.0000

Data Index: 978276 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1279751 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.5162. Min Act: -0.0000

Data Index: 787884 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.4088. Min Act: -0.0000

Data Index: 1967714 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.3461. Min Act: -0.0000

Data Index: 303368 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.4581. Min Act: -0.0000

Data Index: 256701 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.4480. Min Act: -0.0000

Data Index: 1514401 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1875567 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1857686 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1435829 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1220200 (The Pile)

Max Activating Token Index: 191

Text #16

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1032752 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.3387. Min Act: -0.0000

Data Index: 1532124 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.4049. Min Act: -0.0000

Data Index: 1670677 (The Pile)

Max Activating Token Index: 448

Text #19

Max Range: 3.1933. Min Range: -3.1933

Max Act: 1.1641. Min Act: -0.0000

Data Index: 220663 (The Pile)

Max Activating Token Index: 65