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

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

Neuron 2010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4616. Min Act: -0.0000

Data Index: 669788 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4275. Min Act: -0.0000

Data Index: 656792 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3903. Min Act: -0.0000

Data Index: 785999 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3721. Min Act: -0.0000

Data Index: 663629 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1259435 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3402. Min Act: -0.0000

Data Index: 144146 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3653. Min Act: -0.0000

Data Index: 239126 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3473. Min Act: -0.0000

Data Index: 31313 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3445. Min Act: -0.0000

Data Index: 203468 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3307. Min Act: -0.0000

Data Index: 87154 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3544. Min Act: -0.0000

Data Index: 429098 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3378. Min Act: -0.0000

Data Index: 527186 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3353. Min Act: -0.0000

Data Index: 267956 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3278. Min Act: -0.0000

Data Index: 318656 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1253106 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1149701 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1243395 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1290000 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3106. Min Act: -0.0000

Data Index: 295047 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3146. Min Act: -0.0000

Data Index: 882929 (C4 (Web Text))

Max Activating Token Index: 59