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

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

Neuron 874 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: 0.2380. Min Range: -0.2380

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1285854 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2063. Min Act: -0.0001

Data Index: 375189 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2228. Min Act: -0.0001

Data Index: 765200 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2251. Min Act: -0.0001

Data Index: 623407 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1947. Min Act: -0.0001

Data Index: 901878 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2316. Min Act: -0.0001

Data Index: 466795 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2128. Min Act: -0.0001

Data Index: 15074 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1929. Min Act: -0.0001

Data Index: 891687 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2317. Min Act: -0.0001

Data Index: 367696 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2010. Min Act: -0.0001

Data Index: 444340 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2216. Min Act: -0.0001

Data Index: 147207 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2309. Min Act: -0.0001

Data Index: 1130407 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1579082 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2126. Min Act: -0.0001

Data Index: 519520 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2065. Min Act: -0.0001

Data Index: 946891 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1143534 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2115. Min Act: -0.0001

Data Index: 40597 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.1961. Min Act: -0.0001

Data Index: 595945 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2247. Min Act: -0.0001

Data Index: 853729 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.2380. Min Range: -0.2380

Max Act: 0.2142. Min Act: -0.0001

Data Index: 844609 (C4 (Web Text))

Max Activating Token Index: 204