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

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

Neuron 1839 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.7081. Min Act: -0.0001

Data Index: 286552 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.5411. Min Act: -0.0001

Data Index: 1265377 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.9837. Min Act: -0.0001

Data Index: 618015 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8666. Min Act: -0.0001

Data Index: 1071292 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8448. Min Act: -0.0001

Data Index: 53320 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.1197. Min Act: -0.0001

Data Index: 1023496 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.0361. Min Act: -0.0001

Data Index: 95944 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.1100. Min Act: -0.0001

Data Index: 132383 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.7005. Min Act: -0.0001

Data Index: 602519 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 3.7081. Min Range: -3.7081

Max Act: 3.1103. Min Act: -0.0001

Data Index: 275493 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8103. Min Act: -0.0001

Data Index: 1342091 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8028. Min Act: -0.0001

Data Index: 733992 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.9221. Min Act: -0.0001

Data Index: 798904 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8895. Min Act: -0.0001

Data Index: 579083 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.4650. Min Act: -0.0001

Data Index: 612167 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.7136. Min Act: -0.0001

Data Index: 814263 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.7121. Min Act: -0.0001

Data Index: 1156650 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8417. Min Act: -0.0001

Data Index: 236338 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.6903. Min Act: -0.0001

Data Index: 1212946 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.7081. Min Range: -3.7081

Max Act: 2.8330. Min Act: -0.0001

Data Index: 971677 (C4 (Web Text))

Max Activating Token Index: 483