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

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

Neuron 1024 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: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0000

Data Index: 949098 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1290. Min Act: -0.0000

Data Index: 776658 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1241. Min Act: -0.0000

Data Index: 649071 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1097. Min Act: -0.0000

Data Index: 981161 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1184. Min Act: -0.0000

Data Index: 912285 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1308396 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1100. Min Act: -0.0000

Data Index: 428357 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1071. Min Act: -0.0000

Data Index: 884060 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0999. Min Act: -0.0000

Data Index: 63193 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1099507 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1105. Min Act: -0.0000

Data Index: 68133 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0950. Min Act: -0.0000

Data Index: 545390 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1059. Min Act: -0.0000

Data Index: 171633 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1058. Min Act: -0.0000

Data Index: 433253 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0948. Min Act: -0.0000

Data Index: 50979 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0933. Min Act: -0.0000

Data Index: 475637 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0881. Min Act: -0.0000

Data Index: 848380 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1941 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0980. Min Act: -0.0000

Data Index: 747321 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0921. Min Act: -0.0000

Data Index: 257644 (C4 (Web Text))

Max Activating Token Index: 437