Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 935 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1443681 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1521113 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7488. Min Act: -0.0000

Data Index: 137336 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1929614 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7558. Min Act: -0.0000

Data Index: 712471 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1153368 (The Pile)

Max Activating Token Index: 12

Text #6

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6866. Min Act: -0.0000

Data Index: 325795 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1146389 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6925. Min Act: -0.0000

Data Index: 278474 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1132941 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1333672 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6441. Min Act: -0.0000

Data Index: 409150 (The Pile)

Max Activating Token Index: 444

Text #12

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6609. Min Act: -0.0000

Data Index: 635814 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1724435 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7272. Min Act: -0.0000

Data Index: 132208 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1998764 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6683. Min Act: -0.0000

Data Index: 659339 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7007. Min Act: -0.0000

Data Index: 404574 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1166574 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6558. Min Act: -0.0000

Data Index: 450545 (The Pile)

Max Activating Token Index: 375