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

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

Neuron 2489 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4543. Min Range: -2.4543

Max Act: 2.4543. Min Act: -0.0000

Data Index: 851155 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 2.4543. Min Range: -2.4543

Max Act: 2.1134. Min Act: -0.0000

Data Index: 757985 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.9693. Min Act: -0.0000

Data Index: 1194633 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.8165. Min Act: -0.0000

Data Index: 1294374 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.8167. Min Act: -0.0000

Data Index: 1035878 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.8753. Min Act: -0.0000

Data Index: 1103617 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.8098. Min Act: -0.0000

Data Index: 696752 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.6797. Min Act: -0.0000

Data Index: 512003 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.7060. Min Act: -0.0000

Data Index: 792604 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1025822 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5811. Min Act: -0.0000

Data Index: 903212 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.6199. Min Act: -0.0000

Data Index: 374601 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.6241. Min Act: -0.0000

Data Index: 652763 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5628. Min Act: -0.0000

Data Index: 648032 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5521. Min Act: -0.0000

Data Index: 181293 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1336005 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1083764 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5650. Min Act: -0.0000

Data Index: 604819 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 2.4543. Min Range: -2.4543

Max Act: 1.5767. Min Act: -0.0000

Data Index: 1145175 (C4 (Web Text))

Max Activating Token Index: 255