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

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

Neuron 2320 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5443. Min Act: -0.0000

Data Index: 96895 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5108. Min Act: -0.0000

Data Index: 33159 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5212. Min Act: -0.0000

Data Index: 834762 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4801. Min Act: -0.0000

Data Index: 973740 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4717. Min Act: -0.0000

Data Index: 190565 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1233561 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4749. Min Act: -0.0000

Data Index: 614891 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1237602 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1412424 (Python Code)

Max Activating Token Index: 794

Text #9

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1387314 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3445. Min Act: -0.0000

Data Index: 88143 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1388533 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1643841 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3897. Min Act: -0.0000

Data Index: 80839 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3909. Min Act: -0.0000

Data Index: 882859 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3624. Min Act: -0.0000

Data Index: 363856 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4011. Min Act: -0.0000

Data Index: 344595 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1023370 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3719. Min Act: -0.0000

Data Index: 981544 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1202153 (C4 (Web Text))

Max Activating Token Index: 325