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

Dataset: The Pile

Neuron 2333 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.6781. Min Act: -0.0000

Data Index: 1392195 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1649813 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1335414 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.2293. Min Act: -0.0000

Data Index: 844382 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.2026. Min Act: -0.0000

Data Index: 1441455 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1649101 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1826955 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1268194 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9819. Min Act: -0.0000

Data Index: 1692390 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0897. Min Act: -0.0000

Data Index: 861391 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1434354 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9580. Min Act: -0.0000

Data Index: 760938 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9351. Min Act: -0.0000

Data Index: 612088 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0849. Min Act: -0.0000

Data Index: 7800 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9655. Min Act: -0.0000

Data Index: 806238 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.6781. Min Range: -1.6781

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1878442 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1318178 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9534. Min Act: -0.0000

Data Index: 425758 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1168088 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.6781. Min Range: -1.6781

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1945312 (The Pile)

Max Activating Token Index: 614