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

Dataset: The Pile

Neuron 4994 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: 3.5320. Min Range: -3.5320

Max Act: 3.2423. Min Act: -0.0000

Data Index: 908117 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.5320. Min Act: -0.0000

Data Index: 126059 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.7889. Min Act: -0.0000

Data Index: 334519 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.7286. Min Act: -0.0000

Data Index: 55025 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.5879. Min Act: -0.0000

Data Index: 45204 (The Pile)

Max Activating Token Index: 467

Text #5

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.6308. Min Act: -0.0000

Data Index: 44670 (The Pile)

Max Activating Token Index: 596

Text #6

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4688. Min Act: -0.0000

Data Index: 483779 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.8499. Min Act: -0.0000

Data Index: 17720 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.7012. Min Act: -0.0000

Data Index: 514603 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.5180. Min Act: -0.0000

Data Index: 1439060 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4207. Min Act: -0.0000

Data Index: 42015 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4196. Min Act: -0.0000

Data Index: 412694 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4135. Min Act: -0.0000

Data Index: 412315 (The Pile)

Max Activating Token Index: 14

Text #13

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.5381. Min Act: -0.0000

Data Index: 1791095 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.5204. Min Act: -0.0000

Data Index: 1370453 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.6160. Min Act: -0.0000

Data Index: 1586307 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4872. Min Act: -0.0000

Data Index: 941764 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.4461. Min Act: -0.0000

Data Index: 198827 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.2959. Min Act: -0.0000

Data Index: 1745920 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.2833. Min Act: -0.0000

Data Index: 1753224 (The Pile)

Max Activating Token Index: 391