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

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

Neuron 3281 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3608. Min Act: -0.0001

Data Index: 477300 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3498. Min Act: -0.0001

Data Index: 259336 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3517. Min Act: -0.0000

Data Index: 939216 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3423. Min Act: -0.0000

Data Index: 306826 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3415. Min Act: -0.0000

Data Index: 267120 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3076. Min Act: -0.0000

Data Index: 205458 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3073. Min Act: -0.0000

Data Index: 832914 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3067. Min Act: -0.0001

Data Index: 415856 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2989. Min Act: -0.0001

Data Index: 598792 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3056. Min Act: -0.0001

Data Index: 574870 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1288670 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3142. Min Act: -0.0001

Data Index: 570137 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1178244 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2946. Min Act: -0.0000

Data Index: 997714 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1306068 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2931. Min Act: -0.0000

Data Index: 376258 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2920. Min Act: -0.0000

Data Index: 326515 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2853. Min Act: -0.0001

Data Index: 1162191 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.3022. Min Act: -0.0000

Data Index: 807620 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.3608. Min Range: -0.3608

Max Act: 0.2862. Min Act: -0.0001

Data Index: 176121 (C4 (Web Text))

Max Activating Token Index: 763