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

Dataset: The Pile

Neuron 2387 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: 4.6590. Min Range: -4.6590

Max Act: 4.6590. Min Act: -0.0000

Data Index: 1167584 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.4553. Min Act: -0.0000

Data Index: 1160085 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.3948. Min Act: -0.0000

Data Index: 815990 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.5085. Min Act: -0.0000

Data Index: 1382784 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.0165. Min Act: -0.0000

Data Index: 1781513 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.4582. Min Act: -0.0000

Data Index: 559980 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.9411. Min Act: -0.0000

Data Index: 649411 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2138. Min Act: -0.0000

Data Index: 1368244 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.1452. Min Act: -0.0000

Data Index: 1440590 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.1267. Min Act: -0.0000

Data Index: 98701 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.1247. Min Act: -0.0000

Data Index: 1051860 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.4198. Min Act: -0.0000

Data Index: 1683972 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.9355. Min Act: -0.0000

Data Index: 407178 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.9349. Min Act: -0.0000

Data Index: 1049813 (The Pile)

Max Activating Token Index: 470

Text #14

Max Range: 4.6590. Min Range: -4.6590

Max Act: 4.2327. Min Act: -0.0000

Data Index: 1379619 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.8623. Min Act: -0.0000

Data Index: 851812 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.8003. Min Act: -0.0000

Data Index: 308953 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.9659. Min Act: -0.0000

Data Index: 1815541 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.9354. Min Act: -0.0000

Data Index: 1794258 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 4.6590. Min Range: -4.6590

Max Act: 3.7646. Min Act: -0.0000

Data Index: 1340578 (The Pile)

Max Activating Token Index: 576