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

Dataset: The Pile

Neuron 1770 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: 0.8430. Min Range: -0.8430

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1605355 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1924229 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1502384 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7135. Min Act: -0.0000

Data Index: 373398 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1712009 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5392. Min Act: -0.0000

Data Index: 576978 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7301. Min Act: -0.0000

Data Index: 1600973 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1175944 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1036169 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1744159 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1629332 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1577790 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6055. Min Act: -0.0000

Data Index: 991675 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6530. Min Act: -0.0000

Data Index: 683415 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6248. Min Act: -0.0000

Data Index: 766912 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5720. Min Act: -0.0000

Data Index: 187278 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1889633 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6461. Min Act: -0.0000

Data Index: 397984 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1397231 (The Pile)

Max Activating Token Index: 232

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5274. Min Act: -0.0000

Data Index: 1908276 (The Pile)

Max Activating Token Index: 49