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

Dataset: The Pile

Neuron 3470 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: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0000

Data Index: 765148 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9047. Min Act: -0.0000

Data Index: 311969 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1546465 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8425. Min Act: -0.0000

Data Index: 746556 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8611. Min Act: -0.0000

Data Index: 828179 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1106576 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8316. Min Act: -0.0000

Data Index: 425158 (The Pile)

Max Activating Token Index: 284

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8556. Min Act: -0.0000

Data Index: 745433 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8233. Min Act: -0.0000

Data Index: 224242 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8212. Min Act: -0.0000

Data Index: 16918 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8067. Min Act: -0.0000

Data Index: 1049277 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7836. Min Act: -0.0000

Data Index: 631596 (The Pile)

Max Activating Token Index: 19

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8022. Min Act: -0.0000

Data Index: 148437 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8093. Min Act: -0.0000

Data Index: 702083 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1592100 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1980446 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7709. Min Act: -0.0000

Data Index: 273551 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1848745 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1834414 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7625. Min Act: -0.0000

Data Index: 39508 (The Pile)

Max Activating Token Index: 964