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

Dataset: The Pile

Neuron 5061 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: 0.9829. Min Range: -0.9829

Max Act: 0.9829. Min Act: -0.0001

Data Index: 1654714 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1875338 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1005941 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1216656 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1547471 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1763800 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5559. Min Act: -0.0000

Data Index: 798369 (The Pile)

Max Activating Token Index: 370

Text #7

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1556229 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5368. Min Act: -0.0000

Data Index: 928054 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1067193 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5098. Min Act: -0.0001

Data Index: 38222 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1574581 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1581587 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1755191 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1885588 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4603. Min Act: -0.0000

Data Index: 266674 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1448082 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1714629 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4818. Min Act: -0.0000

Data Index: 729155 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1355450 (The Pile)

Max Activating Token Index: 1022