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

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

Neuron 2995 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8683. Min Act: -0.0000

Data Index: 958531 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.6637. Min Act: -0.0000

Data Index: 1244696 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1356180 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.6007. Min Act: -0.0000

Data Index: 605512 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.4884. Min Act: -0.0000

Data Index: 869051 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.2537. Min Act: -0.0000

Data Index: 326116 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1761. Min Act: -0.0000

Data Index: 189366 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1591. Min Act: -0.0000

Data Index: 680057 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1053. Min Act: -0.0000

Data Index: 345720 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1022064 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.2479. Min Act: -0.0000

Data Index: 280788 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.8249. Min Act: -0.0000

Data Index: 804353 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0191. Min Act: -0.0000

Data Index: 537844 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.9078. Min Act: -0.0000

Data Index: 200 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1311454 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.8473. Min Act: -0.0000

Data Index: 592165 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0765. Min Act: -0.0000

Data Index: 908369 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.8938. Min Act: -0.0000

Data Index: 717305 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.8984. Min Act: -0.0000

Data Index: 181900 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 2.8683. Min Range: -2.8683

Max Act: 1.9029. Min Act: -0.0000

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 87