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

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

Neuron 339 in Layer 0

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: 0.2153. Min Range: -0.2153

Max Act: 0.2153. Min Act: -0.0002

Data Index: 418503 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.2018. Min Act: -0.0001

Data Index: 881185 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1126137 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1949. Min Act: -0.0001

Data Index: 651006 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1812. Min Act: -0.0001

Data Index: 373843 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1785. Min Act: -0.0001

Data Index: 716371 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1795. Min Act: -0.0001

Data Index: 947850 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1757. Min Act: -0.0001

Data Index: 211313 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1821. Min Act: -0.0001

Data Index: 516827 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1776. Min Act: -0.0001

Data Index: 307497 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1755. Min Act: -0.0001

Data Index: 887773 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1695. Min Act: -0.0001

Data Index: 637501 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1709. Min Act: -0.0001

Data Index: 726374 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1242370 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1705. Min Act: -0.0001

Data Index: 608799 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1728. Min Act: -0.0001

Data Index: 697120 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1701. Min Act: -0.0001

Data Index: 269676 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1727. Min Act: -0.0001

Data Index: 356551 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1670. Min Act: -0.0001

Data Index: 482734 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.2153. Min Range: -0.2153

Max Act: 0.1643. Min Act: -0.0001

Data Index: 832546 (C4 (Web Text))

Max Activating Token Index: 644