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

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

Neuron 4145 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: 0.4621. Min Range: -0.4621

Max Act: 0.4291. Min Act: -0.0001

Data Index: 35525 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1125756 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4621. Min Act: -0.0000

Data Index: 213325 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3967. Min Act: -0.0000

Data Index: 931783 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1044506 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3283. Min Act: -0.0000

Data Index: 259620 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3651. Min Act: -0.0000

Data Index: 692486 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3566. Min Act: -0.0001

Data Index: 570418 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3471. Min Act: -0.0000

Data Index: 674680 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3532. Min Act: -0.0001

Data Index: 976600 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3127. Min Act: -0.0000

Data Index: 491069 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1029896 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3529. Min Act: -0.0000

Data Index: 705541 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3410. Min Act: -0.0001

Data Index: 366047 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.2782. Min Act: -0.0000

Data Index: 301470 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.2790. Min Act: -0.0000

Data Index: 133625 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.2341. Min Act: -0.0000

Data Index: 325173 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.1879. Min Act: -0.0000

Data Index: 140457 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.1936. Min Act: -0.0000

Data Index: 565938 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.1670. Min Act: -0.0000

Data Index: 319746 (C4 (Web Text))

Max Activating Token Index: 21