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

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

Neuron 349 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: 0.7451. Min Range: -0.7451

Max Act: 0.7451. Min Act: -0.0002

Data Index: 903328 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6982. Min Act: -0.0002

Data Index: 835393 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6852. Min Act: -0.0002

Data Index: 1251371 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6716. Min Act: -0.0002

Data Index: 1350044 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6736. Min Act: -0.0002

Data Index: 799701 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6653. Min Act: -0.0002

Data Index: 844949 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6683. Min Act: -0.0002

Data Index: 82116 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6432. Min Act: -0.0002

Data Index: 674032 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6314. Min Act: -0.0002

Data Index: 160951 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6249. Min Act: -0.0002

Data Index: 187928 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6161. Min Act: -0.0002

Data Index: 87066 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6170. Min Act: -0.0002

Data Index: 1046086 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6003. Min Act: -0.0002

Data Index: 1028905 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.6067. Min Act: -0.0002

Data Index: 229532 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5946. Min Act: -0.0002

Data Index: 681459 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5901. Min Act: -0.0002

Data Index: 543593 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5946. Min Act: -0.0002

Data Index: 428525 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5828. Min Act: -0.0002

Data Index: 1142719 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5705. Min Act: -0.0002

Data Index: 568606 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.7451. Min Range: -0.7451

Max Act: 0.5789. Min Act: -0.0002

Data Index: 1068306 (C4 (Web Text))

Max Activating Token Index: 63