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

Dataset: The Pile

Neuron 340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.9417. Min Act: -0.0000

Data Index: 1156344 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.8373. Min Act: -0.0000

Data Index: 462518 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5974. Min Act: -0.0000

Data Index: 1471272 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.7205. Min Act: -0.0000

Data Index: 866020 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.7138. Min Act: -0.0000

Data Index: 429050 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5710. Min Act: -0.0000

Data Index: 1634220 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5131. Min Act: -0.0000

Data Index: 1797395 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.8070. Min Act: -0.0000

Data Index: 1131743 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6278. Min Act: -0.0000

Data Index: 1430677 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.3949. Min Act: -0.0000

Data Index: 1994359 (The Pile)

Max Activating Token Index: 885

Text #10

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.3696. Min Act: -0.0000

Data Index: 1729944 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.5576. Min Act: -0.0000

Data Index: 1490154 (The Pile)

Max Activating Token Index: 679

Text #12

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.3900. Min Act: -0.0000

Data Index: 1829180 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6510. Min Act: -0.0000

Data Index: 530098 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.6100. Min Act: -0.0000

Data Index: 1887340 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.7131. Min Act: -0.0000

Data Index: 762809 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4428. Min Act: -0.0000

Data Index: 820275 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.3035. Min Act: -0.0000

Data Index: 1717404 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.4278. Min Act: -0.0000

Data Index: 73824 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 3.9417. Min Range: -3.9417

Max Act: 3.3898. Min Act: -0.0000

Data Index: 1810545 (The Pile)

Max Activating Token Index: 361