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

Dataset: The Pile

Neuron 2744 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: 0.6504. Min Range: -0.6504

Max Act: 0.6036. Min Act: -0.0000

Data Index: 23897 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6504. Min Act: 0.0000

Data Index: 1565242 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1211359 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1914866 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4787. Min Act: 0.0000

Data Index: 410001 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1653545 (The Pile)

Max Activating Token Index: 617

Text #6

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1455932 (The Pile)

Max Activating Token Index: 884

Text #7

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1400340 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4852. Min Act: -0.0000

Data Index: 685318 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5049. Min Act: -0.0000

Data Index: 441039 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4643. Min Act: -0.0000

Data Index: 49316 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1214460 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1706152 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4637. Min Act: 0.0000

Data Index: 617521 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4500. Min Act: 0.0000

Data Index: 1884486 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1276827 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4318. Min Act: 0.0001

Data Index: 403791 (The Pile)

Max Activating Token Index: 755

Text #17

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1034057 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1442119 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4122. Min Act: 0.0000

Data Index: 1744456 (The Pile)

Max Activating Token Index: 491