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

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

Neuron 1640 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: 0.1177. Min Range: -0.1177

Max Act: 0.1177. Min Act: -0.0001

Data Index: 777608 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1134. Min Act: -0.0001

Data Index: 576258 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1049. Min Act: -0.0001

Data Index: 739291 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1071. Min Act: -0.0001

Data Index: 188437 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1001. Min Act: -0.0000

Data Index: 750289 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1430840 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1042. Min Act: -0.0000

Data Index: 114383 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1336139 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0996. Min Act: -0.0001

Data Index: 792153 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.1013. Min Act: -0.0001

Data Index: 226944 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0925. Min Act: -0.0000

Data Index: 680777 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1238129 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0952. Min Act: -0.0001

Data Index: 872242 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1159625 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0975. Min Act: -0.0001

Data Index: 292709 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0995. Min Act: -0.0001

Data Index: 809786 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1435670 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1431203 (Python Code)

Max Activating Token Index: 584

Text #18

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1201153 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1177. Min Range: -0.1177

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1081904 (C4 (Web Text))

Max Activating Token Index: 161