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

Dataset: The Pile

Neuron 3081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.4185. Min Range: -9.4185

Max Act: 9.4185. Min Act: -0.0000

Data Index: 841174 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.9181. Min Act: -0.0000

Data Index: 489505 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.6921. Min Act: -0.0000

Data Index: 874866 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.2599. Min Act: -0.0000

Data Index: 1228683 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.3939. Min Act: -0.0000

Data Index: 231628 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.5613. Min Act: -0.0000

Data Index: 607627 (The Pile)

Max Activating Token Index: 690

Text #6

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.5310. Min Act: -0.0000

Data Index: 1569877 (The Pile)

Max Activating Token Index: 408

Text #7

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.5208. Min Act: -0.0000

Data Index: 1604198 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.0633. Min Act: -0.0000

Data Index: 1283614 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.0783. Min Act: -0.0000

Data Index: 1592680 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.6339. Min Act: -0.0000

Data Index: 731505 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.2475. Min Act: -0.0000

Data Index: 531819 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.6203. Min Act: -0.0000

Data Index: 1191489 (The Pile)

Max Activating Token Index: 824

Text #13

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.4146. Min Act: -0.0000

Data Index: 1954268 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.1515. Min Act: -0.0000

Data Index: 214107 (The Pile)

Max Activating Token Index: 789

Text #15

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.1411. Min Act: -0.0000

Data Index: 1522589 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.4712. Min Act: -0.0000

Data Index: 719760 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.2915. Min Act: -0.0000

Data Index: 768927 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 9.4185. Min Range: -9.4185

Max Act: 6.9027. Min Act: -0.0000

Data Index: 255997 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 9.4185. Min Range: -9.4185

Max Act: 7.3608. Min Act: -0.0000

Data Index: 1386920 (The Pile)

Max Activating Token Index: 719