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

Dataset: The Pile

Neuron 3429 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: 1.1804. Min Range: -1.1804

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1277141 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.9653. Min Act: -0.0000

Data Index: 554321 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.9062. Min Act: -0.0000

Data Index: 630068 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.8539. Min Act: -0.0000

Data Index: 732156 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1401545 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7695. Min Act: -0.0000

Data Index: 929706 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6318. Min Act: -0.0000

Data Index: 941105 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1639762 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7078. Min Act: -0.0000

Data Index: 87070 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1968928 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1027331 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7548. Min Act: -0.0000

Data Index: 68892 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6795. Min Act: -0.0000

Data Index: 171069 (The Pile)

Max Activating Token Index: 351

Text #13

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1668432 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6761. Min Act: -0.0000

Data Index: 160917 (The Pile)

Max Activating Token Index: 456

Text #15

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1643896 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1864270 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6911. Min Act: -0.0000

Data Index: 212480 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.6672. Min Act: -0.0000

Data Index: 956588 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.1804. Min Range: -1.1804

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1836116 (The Pile)

Max Activating Token Index: 705