Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1216 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2078. Min Act: -0.0002

Data Index: 16200 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2184. Min Act: -0.0002

Data Index: 152867 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1819. Min Act: -0.0003

Data Index: 1225237 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1864. Min Act: -0.0002

Data Index: 305466 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1714. Min Act: -0.0002

Data Index: 255522 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1341. Min Act: -0.0002

Data Index: 624929 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1434. Min Act: -0.0002

Data Index: 1313887 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1544. Min Act: -0.0002

Data Index: 914380 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1477. Min Act: -0.0002

Data Index: 377097 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1340. Min Act: -0.0002

Data Index: 385041 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1081. Min Act: -0.0002

Data Index: 388069 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1109. Min Act: -0.0003

Data Index: 133557 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0846. Min Act: -0.0002

Data Index: 1303452 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1038. Min Act: -0.0002

Data Index: 987897 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1119. Min Act: -0.0003

Data Index: 95184 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0810. Min Act: -0.0003

Data Index: 277671 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0783. Min Act: -0.0002

Data Index: 188742 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1174. Min Act: -0.0002

Data Index: 916483 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1049. Min Act: -0.0002

Data Index: 371333 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1139. Min Act: -0.0002

Data Index: 1357211 (C4 (Web Text))

Max Activating Token Index: 29