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

Dataset: The Pile

Neuron 2323 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: 0.6349. Min Range: -0.6349

Max Act: 0.6349. Min Act: -0.0000

Data Index: 593568 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5613. Min Act: -0.0000

Data Index: 565736 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5518. Min Act: -0.0000

Data Index: 722280 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5658. Min Act: -0.0000

Data Index: 284225 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5658. Min Act: -0.0000

Data Index: 108984 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5644. Min Act: -0.0000

Data Index: 169435 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5732. Min Act: -0.0000

Data Index: 939689 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1491499 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5479. Min Act: -0.0000

Data Index: 410813 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5518. Min Act: -0.0000

Data Index: 840718 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5354. Min Act: -0.0000

Data Index: 432443 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5560. Min Act: -0.0000

Data Index: 332349 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5449. Min Act: -0.0000

Data Index: 817144 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1992481 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5488. Min Act: -0.0000

Data Index: 88440 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1568575 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5002. Min Act: -0.0000

Data Index: 513853 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5025. Min Act: -0.0000

Data Index: 346228 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.5493. Min Act: -0.0000

Data Index: 681576 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.6349. Min Range: -0.6349

Max Act: 0.4813. Min Act: -0.0000

Data Index: 412762 (The Pile)

Max Activating Token Index: 892