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

Dataset: The Pile

Neuron 4099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9694. Min Act: -0.0000

Data Index: 114273 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8027. Min Act: -0.0000

Data Index: 331071 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1161786 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8217. Min Act: -0.0000

Data Index: 938488 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1246387 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7557. Min Act: -0.0000

Data Index: 714188 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7543. Min Act: -0.0000

Data Index: 552497 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1310712 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7411. Min Act: -0.0000

Data Index: 765156 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7196. Min Act: -0.0000

Data Index: 515848 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1560354 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1313579 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1731225 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6201. Min Act: -0.0000

Data Index: 344643 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7397. Min Act: -0.0000

Data Index: 892622 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7181. Min Act: -0.0000

Data Index: 947259 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6903. Min Act: -0.0000

Data Index: 546896 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6662. Min Act: -0.0000

Data Index: 511473 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7131. Min Act: -0.0000

Data Index: 816499 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6869. Min Act: -0.0000

Data Index: 633159 (The Pile)

Max Activating Token Index: 154