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

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

Neuron 3094 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0327. Min Range: -3.0327

Max Act: 3.0327. Min Act: -0.0001

Data Index: 628787 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.7412. Min Act: -0.0001

Data Index: 732522 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.5073. Min Act: -0.0001

Data Index: 567511 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.4540. Min Act: -0.0001

Data Index: 335518 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.3300. Min Act: -0.0001

Data Index: 484301 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.3168. Min Act: -0.0001

Data Index: 910007 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.3434. Min Act: -0.0001

Data Index: 353521 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.4300. Min Act: -0.0001

Data Index: 1244051 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.2053. Min Act: -0.0001

Data Index: 450017 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.2592. Min Act: -0.0001

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.2509. Min Act: -0.0001

Data Index: 484874 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.0590. Min Act: -0.0001

Data Index: 151958 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.2850. Min Act: -0.0001

Data Index: 722395 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.0446. Min Act: -0.0001

Data Index: 56812 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.1995. Min Act: -0.0001

Data Index: 871798 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.1324. Min Act: -0.0001

Data Index: 1152317 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.0730. Min Act: -0.0001

Data Index: 23626 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.1711. Min Act: -0.0001

Data Index: 1061194 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.0227. Min Act: -0.0000

Data Index: 112450 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.0327. Min Range: -3.0327

Max Act: 2.1719. Min Act: -0.0001

Data Index: 269039 (C4 (Web Text))

Max Activating Token Index: 1021