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

Dataset: The Pile

Neuron 310 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: 1.2117. Min Range: -1.2117

Max Act: 1.2117. Min Act: 0.0000

Data Index: 154083 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.0827. Min Act: -0.0000

Data Index: 562423 (The Pile)

Max Activating Token Index: 906

Text #2

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1208595 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.0727. Min Act: -0.0000

Data Index: 838008 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.9771. Min Act: -0.0000

Data Index: 915032 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.9704. Min Act: -0.0000

Data Index: 576249 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1917107 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8973. Min Act: -0.0000

Data Index: 411862 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8733. Min Act: 0.0000

Data Index: 1421762 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8507. Min Act: -0.0000

Data Index: 655582 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7993. Min Act: 0.0000

Data Index: 459758 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.2117. Min Range: -1.2117

Max Act: 1.0021. Min Act: -0.0000

Data Index: 133476 (The Pile)

Max Activating Token Index: 819

Text #12

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1608153 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8127. Min Act: -0.0000

Data Index: 648776 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1723038 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.8470. Min Act: -0.0000

Data Index: 289163 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1266072 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1603965 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1099688 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.2117. Min Range: -1.2117

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1988343 (The Pile)

Max Activating Token Index: 347