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

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

Neuron 474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4790. Min Act: -0.0001

Data Index: 385643 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4692. Min Act: -0.0001

Data Index: 964487 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4091. Min Act: -0.0001

Data Index: 59975 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1286038 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4515. Min Act: -0.0001

Data Index: 603003 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4081. Min Act: -0.0000

Data Index: 616408 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4269. Min Act: -0.0001

Data Index: 819042 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4219. Min Act: -0.0001

Data Index: 558440 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4065. Min Act: -0.0000

Data Index: 343541 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4045. Min Act: -0.0001

Data Index: 743164 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4110. Min Act: -0.0001

Data Index: 93959 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3976. Min Act: -0.0001

Data Index: 342463 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1048020 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4130. Min Act: -0.0001

Data Index: 322479 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1188858 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3713. Min Act: -0.0001

Data Index: 459104 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3832. Min Act: -0.0001

Data Index: 824697 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3785. Min Act: -0.0001

Data Index: 1095190 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3707. Min Act: -0.0001

Data Index: 875602 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3829. Min Act: -0.0001

Data Index: 1234726 (C4 (Web Text))

Max Activating Token Index: 257