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

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

Neuron 1538 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2934. Min Act: -0.0000

Data Index: 60279 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2146. Min Act: -0.0000

Data Index: 21862 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1985. Min Act: -0.0000

Data Index: 807176 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2193. Min Act: -0.0000

Data Index: 629049 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2063. Min Act: -0.0000

Data Index: 94641 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2070. Min Act: -0.0000

Data Index: 239641 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2052. Min Act: -0.0001

Data Index: 67264 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2034. Min Act: -0.0000

Data Index: 714779 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1874. Min Act: -0.0000

Data Index: 258961 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1224904 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1927. Min Act: -0.0000

Data Index: 584624 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2093. Min Act: -0.0001

Data Index: 615471 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1431594 (Python Code)

Max Activating Token Index: 821

Text #13

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1761. Min Act: -0.0000

Data Index: 490761 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1929. Min Act: -0.0000

Data Index: 61061 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1912. Min Act: -0.0000

Data Index: 933220 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1359667 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1261558 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.2010. Min Act: -0.0000

Data Index: 115183 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.2934. Min Range: -0.2934

Max Act: 0.1793. Min Act: -0.0000

Data Index: 807002 (C4 (Web Text))

Max Activating Token Index: 904