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

Dataset: The Pile

Neuron 921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9586. Min Act: 0.0000

Data Index: 1622225 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.9102. Min Act: -0.0000

Data Index: 718192 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1346146 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8248. Min Act: -0.0000

Data Index: 90801 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8668. Min Act: -0.0000

Data Index: 265817 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.8592. Min Act: 0.0000

Data Index: 1904408 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1231117 (The Pile)

Max Activating Token Index: 731

Text #7

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7504. Min Act: -0.0000

Data Index: 550926 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6960. Min Act: -0.0000

Data Index: 218643 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7182. Min Act: 0.0001

Data Index: 1767311 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1445727 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1904546 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1755166 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6757. Min Act: 0.0000

Data Index: 1570403 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6886. Min Act: -0.0000

Data Index: 576838 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6960. Min Act: 0.0001

Data Index: 739181 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1565776 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6421. Min Act: -0.0000

Data Index: 475212 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6774. Min Act: -0.0000

Data Index: 475529 (The Pile)

Max Activating Token Index: 499

Text #19

Max Range: 0.9586. Min Range: -0.9586

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1945163 (The Pile)

Max Activating Token Index: 955