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

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

Neuron 257 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1261088 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1231037 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1022223 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1140092 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1064. Min Act: -0.0002

Data Index: 375066 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1025. Min Act: -0.0002

Data Index: 377576 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1010. Min Act: -0.0002

Data Index: 346231 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1094. Min Act: -0.0002

Data Index: 17768 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1041. Min Act: -0.0002

Data Index: 142460 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1038. Min Act: -0.0002

Data Index: 928979 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1037. Min Act: -0.0002

Data Index: 1099090 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1024. Min Act: -0.0002

Data Index: 951636 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1012. Min Act: -0.0002

Data Index: 110248 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1301966 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0989. Min Act: -0.0002

Data Index: 990926 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1242487 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1057796 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1208385 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1339603 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1133765 (C4 (Web Text))

Max Activating Token Index: 377