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

Dataset: The Pile

Neuron 876 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: 1.7101. Min Range: -1.7101

Max Act: 1.5910. Min Act: -0.0000

Data Index: 896275 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.6374. Min Act: -0.0000

Data Index: 91152 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.6198. Min Act: -0.0000

Data Index: 272916 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.7101. Min Act: -0.0000

Data Index: 331302 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1666534 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.6667. Min Act: -0.0000

Data Index: 1970075 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4731. Min Act: -0.0000

Data Index: 674195 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1391515 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5087. Min Act: -0.0000

Data Index: 606521 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5403. Min Act: -0.0000

Data Index: 1396636 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4170. Min Act: -0.0000

Data Index: 139370 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5051. Min Act: -0.0000

Data Index: 145802 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3981. Min Act: -0.0000

Data Index: 228948 (The Pile)

Max Activating Token Index: 1013

Text #13

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1289169 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3939. Min Act: -0.0000

Data Index: 844426 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1271827 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.5111. Min Act: -0.0000

Data Index: 233284 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3428. Min Act: -0.0000

Data Index: 1658219 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.4237. Min Act: -0.0000

Data Index: 688493 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 1.7101. Min Range: -1.7101

Max Act: 1.3378. Min Act: -0.0000

Data Index: 996924 (The Pile)

Max Activating Token Index: 286