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

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

Neuron 5012 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: 1.2647. Min Range: -1.2647

Max Act: 1.2647. Min Act: -0.0000

Data Index: 32653 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.2296. Min Act: -0.0000

Data Index: 766105 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.2010. Min Act: -0.0000

Data Index: 478068 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1467297 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.1728. Min Act: -0.0000

Data Index: 650822 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0932. Min Act: -0.0000

Data Index: 614146 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0964. Min Act: -0.0000

Data Index: 387258 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0823. Min Act: -0.0000

Data Index: 687765 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0731. Min Act: -0.0000

Data Index: 894162 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0500. Min Act: -0.0000

Data Index: 386543 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1294567 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1070975 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0430. Min Act: -0.0000

Data Index: 403336 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1338970 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0086. Min Act: -0.0000

Data Index: 725034 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9575. Min Act: -0.0000

Data Index: 870885 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9865. Min Act: -0.0000

Data Index: 1089373 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0161. Min Act: -0.0000

Data Index: 252030 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.2647. Min Range: -1.2647

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1231368 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.2647. Min Range: -1.2647

Max Act: 0.9748. Min Act: -0.0000

Data Index: 97716 (C4 (Web Text))

Max Activating Token Index: 472