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

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

Neuron 2048 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: 0.2265. Min Range: -0.2265

Max Act: 0.2265. Min Act: -0.0001

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2163. Min Act: -0.0001

Data Index: 832392 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2062. Min Act: -0.0001

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2104. Min Act: -0.0001

Data Index: 370693 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2060. Min Act: -0.0001

Data Index: 635940 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1966. Min Act: -0.0001

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1972. Min Act: -0.0001

Data Index: 87731 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1889. Min Act: -0.0001

Data Index: 621430 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1948. Min Act: -0.0001

Data Index: 244969 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1917. Min Act: -0.0001

Data Index: 958383 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1968. Min Act: -0.0001

Data Index: 242926 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1887. Min Act: -0.0001

Data Index: 328368 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1738. Min Act: -0.0001

Data Index: 989429 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1978. Min Act: -0.0001

Data Index: 466165 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1895. Min Act: -0.0001

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1874. Min Act: -0.0001

Data Index: 156696 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2027. Min Act: -0.0001

Data Index: 864202 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1852. Min Act: -0.0001

Data Index: 960493 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1909. Min Act: -0.0001

Data Index: 666370 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1853. Min Act: -0.0001

Data Index: 49134 (C4 (Web Text))

Max Activating Token Index: 696