Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 266 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7816. Min Act: -0.0001

Data Index: 54 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1566466 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1095044 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7139. Min Act: -0.0001

Data Index: 838115 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7094. Min Act: -0.0001

Data Index: 5280 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6793. Min Act: -0.0001

Data Index: 572581 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.7005. Min Act: -0.0001

Data Index: 1007759 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6821. Min Act: -0.0001

Data Index: 152251 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6779. Min Act: -0.0001

Data Index: 925598 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6751. Min Act: -0.0001

Data Index: 205335 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6767. Min Act: -0.0001

Data Index: 727255 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6353. Min Act: -0.0000

Data Index: 661841 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6717. Min Act: -0.0001

Data Index: 939713 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6423. Min Act: -0.0001

Data Index: 817710 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6156. Min Act: -0.0001

Data Index: 444859 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6319. Min Act: -0.0001

Data Index: 715223 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6770. Min Act: -0.0001

Data Index: 2210 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6488. Min Act: -0.0001

Data Index: 1096328 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6218. Min Act: -0.0001

Data Index: 535323 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.7816. Min Range: -0.7816

Max Act: 0.6262. Min Act: -0.0001

Data Index: 456426 (C4 (Web Text))

Max Activating Token Index: 344