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

Dataset: The Pile

Neuron 4250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3474. Min Range: -3.3474

Max Act: 3.3474. Min Act: -0.0000

Data Index: 1265978 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.6926. Min Act: -0.0000

Data Index: 1037216 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.8238. Min Act: -0.0000

Data Index: 1709860 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 3.3474. Min Range: -3.3474

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1951013 (The Pile)

Max Activating Token Index: 643

Text #4

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1698740 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.8652. Min Act: -0.0000

Data Index: 1635942 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.9595. Min Act: -0.0000

Data Index: 1114170 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.7506. Min Act: -0.0000

Data Index: 971728 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.8403. Min Act: -0.0000

Data Index: 911915 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.6837. Min Act: -0.0000

Data Index: 109126 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.7840. Min Act: -0.0000

Data Index: 1784103 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.8835. Min Act: -0.0000

Data Index: 1679271 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.7963. Min Act: -0.0000

Data Index: 38505 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.5429. Min Act: -0.0000

Data Index: 1137002 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.6266. Min Act: -0.0000

Data Index: 1183526 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.6057. Min Act: -0.0000

Data Index: 725384 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1511212 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.5001. Min Act: -0.0000

Data Index: 1016781 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.5873. Min Act: -0.0000

Data Index: 821816 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 3.3474. Min Range: -3.3474

Max Act: 1.5458. Min Act: -0.0000

Data Index: 251731 (The Pile)

Max Activating Token Index: 382