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

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

Neuron 5073 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2326. Min Act: -0.0000

Data Index: 625629 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2191. Min Act: -0.0000

Data Index: 136212 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1627739 (Python Code)

Max Activating Token Index: 964

Text #3

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1285220 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1414496 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1637074 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2017. Min Act: -0.0000

Data Index: 723325 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2074. Min Act: -0.0000

Data Index: 877035 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1238897 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1196795 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2044. Min Act: -0.0000

Data Index: 519581 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2059. Min Act: -0.0000

Data Index: 386538 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1062008 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2045. Min Act: -0.0000

Data Index: 608929 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1999. Min Act: -0.0000

Data Index: 841619 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1590133 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.2041. Min Act: -0.0000

Data Index: 378599 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1000730 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1974. Min Act: -0.0000

Data Index: 408006 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2326. Min Range: -0.2326

Max Act: 0.1887. Min Act: -0.0000

Data Index: 311853 (C4 (Web Text))

Max Activating Token Index: 778