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

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

Neuron 2274 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1596719 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2615. Min Act: -0.0000

Data Index: 27451 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2277. Min Act: -0.0000

Data Index: 75589 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1063244 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2126. Min Act: -0.0000

Data Index: 914408 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2141. Min Act: -0.0000

Data Index: 671377 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2085. Min Act: -0.0000

Data Index: 736232 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2069. Min Act: -0.0000

Data Index: 616044 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1936. Min Act: -0.0000

Data Index: 238537 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1963. Min Act: -0.0000

Data Index: 900210 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2006. Min Act: -0.0000

Data Index: 363351 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1996. Min Act: -0.0000

Data Index: 64907 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1125180 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1193194 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1857. Min Act: -0.0000

Data Index: 916636 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1329381 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1904. Min Act: -0.0000

Data Index: 59093 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1112234 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1799. Min Act: -0.0000

Data Index: 76396 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.3014. Min Range: -0.3014

Max Act: 0.1832. Min Act: -0.0000

Data Index: 135319 (C4 (Web Text))

Max Activating Token Index: 982