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

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

Neuron 5237 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.4018. Min Act: -0.0000

Data Index: 277067 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1302277 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.3049. Min Act: -0.0000

Data Index: 510926 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2981. Min Act: -0.0000

Data Index: 441858 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2228. Min Act: -0.0000

Data Index: 567766 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2061. Min Act: -0.0000

Data Index: 659330 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2194. Min Act: -0.0000

Data Index: 245813 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2175. Min Act: -0.0000

Data Index: 288929 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2109. Min Act: -0.0000

Data Index: 341782 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1999. Min Act: -0.0000

Data Index: 617491 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1309511 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1991. Min Act: -0.0000

Data Index: 767887 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2103. Min Act: -0.0000

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2082. Min Act: -0.0000

Data Index: 743618 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1938. Min Act: -0.0000

Data Index: 832623 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1942. Min Act: -0.0000

Data Index: 82553 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1241764 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1118292 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1961. Min Act: -0.0000

Data Index: 144175 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.4018. Min Range: -0.4018

Max Act: 0.1950. Min Act: -0.0000

Data Index: 593391 (C4 (Web Text))

Max Activating Token Index: 647