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

Dataset: The Pile

Neuron 325 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1363838 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8492. Min Act: -0.0000

Data Index: 664606 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1043689 (The Pile)

Max Activating Token Index: 351

Text #3

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8294. Min Act: -0.0000

Data Index: 920522 (The Pile)

Max Activating Token Index: 513

Text #4

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8257. Min Act: -0.0000

Data Index: 760615 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1343824 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1663349 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1288425 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7810. Min Act: -0.0000

Data Index: 1626444 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1707858 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7633. Min Act: -0.0000

Data Index: 313121 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1407906 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7623. Min Act: -0.0000

Data Index: 877352 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.8076. Min Act: -0.0000

Data Index: 727798 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7504. Min Act: -0.0000

Data Index: 873272 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1587605 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7312. Min Act: -0.0000

Data Index: 546237 (The Pile)

Max Activating Token Index: 683

Text #17

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7376. Min Act: -0.0000

Data Index: 983378 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7489. Min Act: -0.0000

Data Index: 412006 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.9081. Min Range: -0.9081

Max Act: 0.7585. Min Act: -0.0000

Data Index: 1005722 (The Pile)

Max Activating Token Index: 477