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

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

Neuron 4678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0001

Data Index: 123048 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0985. Min Act: -0.0001

Data Index: 117589 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0879. Min Act: -0.0001

Data Index: 329962 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0883. Min Act: -0.0001

Data Index: 604500 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0790. Min Act: -0.0000

Data Index: 245130 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0726. Min Act: -0.0000

Data Index: 763076 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1017350 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0553. Min Act: -0.0001

Data Index: 238756 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0696. Min Act: -0.0000

Data Index: 150697 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0601. Min Act: -0.0001

Data Index: 378436 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0774. Min Act: -0.0001

Data Index: 280861 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0736. Min Act: -0.0001

Data Index: 876246 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0690. Min Act: -0.0001

Data Index: 976469 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1227403 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0652. Min Act: -0.0001

Data Index: 3606 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0650. Min Act: -0.0001

Data Index: 54942 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0678. Min Act: -0.0000

Data Index: 280547 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0674. Min Act: -0.0001

Data Index: 348445 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0704. Min Act: -0.0001

Data Index: 190483 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0531. Min Act: -0.0001

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 428