Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2003 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0519. Min Range: -3.0519

Max Act: 3.0519. Min Act: -0.0000

Data Index: 1194264 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.8278. Min Act: -0.0000

Data Index: 676998 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.7332. Min Act: -0.0000

Data Index: 506933 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.4085. Min Act: -0.0000

Data Index: 1283362 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.3673. Min Act: -0.0000

Data Index: 215482 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.2459. Min Act: -0.0000

Data Index: 426083 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.2250. Min Act: -0.0000

Data Index: 796348 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.3863. Min Act: -0.0000

Data Index: 1088932 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.2362. Min Act: -0.0000

Data Index: 741154 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.2117. Min Act: -0.0000

Data Index: 885617 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.1716. Min Act: -0.0000

Data Index: 388121 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.0519. Min Range: -3.0519

Max Act: 1.9028. Min Act: -0.0000

Data Index: 550132 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.1153. Min Act: -0.0000

Data Index: 634068 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 3.0519. Min Range: -3.0519

Max Act: 1.9727. Min Act: -0.0000

Data Index: 1254149 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1044266 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 3.0519. Min Range: -3.0519

Max Act: 1.9065. Min Act: -0.0000

Data Index: 1275078 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1346889 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 3.0519. Min Range: -3.0519

Max Act: 1.9516. Min Act: -0.0000

Data Index: 412814 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 3.0519. Min Range: -3.0519

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1283149 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 3.0519. Min Range: -3.0519

Max Act: 1.9938. Min Act: -0.0000

Data Index: 334021 (C4 (Web Text))

Max Activating Token Index: 921