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

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

Neuron 4259 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: 0.3983. Min Range: -0.3983

Max Act: 0.3950. Min Act: -0.0000

Data Index: 280990 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3983. Min Act: -0.0000

Data Index: 966973 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3774. Min Act: 0.0000

Data Index: 1033621 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3855. Min Act: -0.0000

Data Index: 602863 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3718. Min Act: -0.0000

Data Index: 821255 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3669. Min Act: -0.0000

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3610. Min Act: -0.0000

Data Index: 20297 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1307151 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3361. Min Act: -0.0000

Data Index: 125747 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3391. Min Act: -0.0000

Data Index: 580273 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3247. Min Act: -0.0000

Data Index: 223582 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3237. Min Act: -0.0000

Data Index: 900230 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3387. Min Act: -0.0000

Data Index: 321083 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1177874 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3178. Min Act: -0.0000

Data Index: 713261 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1057009 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3233. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3071. Min Act: -0.0000

Data Index: 334661 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3142. Min Act: -0.0000

Data Index: 683673 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.3983. Min Range: -0.3983

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1313854 (C4 (Web Text))

Max Activating Token Index: 404