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

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

Neuron 1526 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: 0.5148. Min Range: -0.5148

Max Act: 0.5148. Min Act: -0.0002

Data Index: 1609007 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4860. Min Act: -0.0002

Data Index: 26944 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4727. Min Act: -0.0002

Data Index: 199235 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4619. Min Act: -0.0002

Data Index: 744090 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4565. Min Act: -0.0002

Data Index: 1503635 (Python Code)

Max Activating Token Index: 852

Text #5

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4405. Min Act: -0.0002

Data Index: 596779 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4420. Min Act: -0.0002

Data Index: 805421 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4410. Min Act: -0.0002

Data Index: 199795 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 235241 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 1221467 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 921781 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 754908 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 1190977 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 108269 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 937526 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 349794 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 1547396 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4412. Min Act: -0.0002

Data Index: 1347464 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4330. Min Act: -0.0002

Data Index: 1470212 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4264. Min Act: -0.0002

Data Index: 823227 (C4 (Web Text))

Max Activating Token Index: 767