Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 909 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4932. Min Act: -0.0001

Data Index: 342168 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4926. Min Act: -0.0001

Data Index: 1329333 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4645. Min Act: -0.0001

Data Index: 290255 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4636. Min Act: -0.0001

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4783. Min Act: -0.0001

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4436. Min Act: -0.0001

Data Index: 427605 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4720. Min Act: -0.0001

Data Index: 931280 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4722. Min Act: -0.0001

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4525. Min Act: -0.0001

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4507. Min Act: -0.0001

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4136. Min Act: -0.0001

Data Index: 1213864 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1249555 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4398. Min Act: -0.0001

Data Index: 530587 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4209. Min Act: -0.0001

Data Index: 1274786 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4074. Min Act: -0.0001

Data Index: 635655 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4360. Min Act: -0.0001

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4350. Min Act: -0.0001

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 708