Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1139 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.4524. Min Act: -0.0001

Data Index: 494947 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2717. Min Act: -0.0001

Data Index: 60103 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1906. Min Act: -0.0001

Data Index: 708246 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2107. Min Act: -0.0001

Data Index: 821485 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2567. Min Act: -0.0001

Data Index: 568543 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.2571. Min Act: -0.0001

Data Index: 1290363 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1215. Min Act: -0.0001

Data Index: 662024 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1929. Min Act: -0.0001

Data Index: 1347519 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1692. Min Act: -0.0001

Data Index: 1076675 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0521. Min Act: -0.0001

Data Index: 738770 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0882. Min Act: -0.0001

Data Index: 1176828 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1043. Min Act: -0.0001

Data Index: 1280231 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0734. Min Act: -0.0001

Data Index: 966378 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0726. Min Act: -0.0001

Data Index: 838796 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0354. Min Act: -0.0001

Data Index: 266883 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0342. Min Act: -0.0001

Data Index: 1300078 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0260. Min Act: -0.0001

Data Index: 738615 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0519. Min Act: -0.0001

Data Index: 1210113 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.1009. Min Act: -0.0001

Data Index: 330255 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.4524. Min Range: -1.4524

Max Act: 1.0543. Min Act: -0.0001

Data Index: 92608 (C4 (Web Text))

Max Activating Token Index: 700