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

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

Neuron 5653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.3013. Min Act: -0.0000

Data Index: 68221 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0924. Min Act: -0.0000

Data Index: 437417 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.3013. Min Range: -1.3013

Max Act: 1.0118. Min Act: -0.0000

Data Index: 74416 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.9061. Min Act: -0.0000

Data Index: 871102 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8771. Min Act: -0.0000

Data Index: 1165354 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8669. Min Act: -0.0000

Data Index: 340827 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8695. Min Act: -0.0000

Data Index: 492051 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1246733 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8669. Min Act: -0.0000

Data Index: 462131 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1309919 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1296549 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1006103 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8236. Min Act: -0.0000

Data Index: 920587 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8517. Min Act: -0.0000

Data Index: 525958 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8506. Min Act: -0.0000

Data Index: 732073 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8470. Min Act: -0.0000

Data Index: 279562 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.8416. Min Act: -0.0000

Data Index: 617646 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.7614. Min Act: -0.0000

Data Index: 637045 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.7796. Min Act: -0.0000

Data Index: 915860 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.3013. Min Range: -1.3013

Max Act: 0.7293. Min Act: -0.0000

Data Index: 754470 (C4 (Web Text))

Max Activating Token Index: 273