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

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

Neuron 1443 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1076465 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2277. Min Act: -0.0001

Data Index: 1138913 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2350. Min Act: -0.0001

Data Index: 699752 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2249. Min Act: -0.0001

Data Index: 1016362 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1422044 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2276. Min Act: -0.0001

Data Index: 45717 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2070. Min Act: -0.0001

Data Index: 111680 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1089877 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2027. Min Act: -0.0001

Data Index: 457334 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1076471 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1994. Min Act: -0.0001

Data Index: 558826 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2062. Min Act: -0.0001

Data Index: 672050 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1995. Min Act: -0.0001

Data Index: 370962 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1073397 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1251005 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1020157 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1989. Min Act: -0.0001

Data Index: 148922 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1853. Min Act: -0.0001

Data Index: 198561 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1854. Min Act: -0.0001

Data Index: 757075 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1036398 (C4 (Web Text))

Max Activating Token Index: 64