Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6047 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.1537. Min Act: -0.0000

Data Index: 891775 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1097649 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0472. Min Act: -0.0000

Data Index: 742835 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0106. Min Act: -0.0001

Data Index: 123340 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0549. Min Act: -0.0001

Data Index: 979729 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9533. Min Act: -0.0000

Data Index: 865139 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0305. Min Act: -0.0001

Data Index: 874786 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1479201 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9304. Min Act: -0.0000

Data Index: 99307 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1099006 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0020. Min Act: -0.0000

Data Index: 618804 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1403647 (Python Code)

Max Activating Token Index: 524

Text #12

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9771. Min Act: -0.0001

Data Index: 1102430 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1567660 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1600187 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1365092 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 1.1537. Min Range: -1.1537

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1426284 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1362618 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1377610 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 1.1537. Min Range: -1.1537

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1617944 (Python Code)

Max Activating Token Index: 878