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

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

Neuron 5642 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4727. Min Act: -0.0000

Data Index: 745938 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4620. Min Act: -0.0000

Data Index: 590534 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4724. Min Act: -0.0000

Data Index: 571533 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4370. Min Act: 0.0000

Data Index: 172071 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4716. Min Act: -0.0000

Data Index: 980411 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4445. Min Act: 0.0000

Data Index: 392100 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4493. Min Act: -0.0000

Data Index: 960575 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4463. Min Act: -0.0000

Data Index: 32428 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4259. Min Act: -0.0000

Data Index: 331933 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4209. Min Act: -0.0000

Data Index: 431235 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3980. Min Act: -0.0000

Data Index: 833877 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1210780 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.4016. Min Act: -0.0000

Data Index: 578112 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3996. Min Act: -0.0000

Data Index: 946594 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3977. Min Act: -0.0000

Data Index: 404896 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1598210 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3940. Min Act: -0.0000

Data Index: 928355 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3594. Min Act: -0.0000

Data Index: 35199 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3864. Min Act: 0.0000

Data Index: 920947 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.4727. Min Range: -0.4727

Max Act: 0.3758. Min Act: -0.0000

Data Index: 859447 (C4 (Web Text))

Max Activating Token Index: 592