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

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

Neuron 621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1259895 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1127469 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1067485 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5578. Min Act: -0.0000

Data Index: 945139 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5519. Min Act: -0.0001

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5265. Min Act: -0.0001

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5022. Min Act: -0.0000

Data Index: 266859 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4931. Min Act: -0.0001

Data Index: 1281686 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4896. Min Act: -0.0001

Data Index: 184033 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5065. Min Act: -0.0001

Data Index: 272875 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4653. Min Act: -0.0001

Data Index: 910085 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4530. Min Act: -0.0000

Data Index: 933771 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4922. Min Act: -0.0001

Data Index: 316160 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4614. Min Act: -0.0000

Data Index: 998692 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4896. Min Act: -0.0000

Data Index: 298936 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1274878 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4865. Min Act: -0.0001

Data Index: 1177585 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.5419. Min Act: -0.0001

Data Index: 254018 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4410. Min Act: -0.0001

Data Index: 681608 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.6740. Min Range: -0.6740

Max Act: 0.4348. Min Act: -0.0001

Data Index: 1074763 (C4 (Web Text))

Max Activating Token Index: 838