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

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

Neuron 5681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.8531. Min Act: -0.0000

Data Index: 1252213 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5457. Min Act: -0.0000

Data Index: 1107993 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5971. Min Act: -0.0000

Data Index: 1331004 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.5076. Min Act: -0.0000

Data Index: 883639 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.6019. Min Act: -0.0000

Data Index: 383898 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.4012. Min Act: -0.0000

Data Index: 1149071 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.3486. Min Act: -0.0000

Data Index: 527619 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.3528. Min Act: -0.0000

Data Index: 779153 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.1577. Min Act: -0.0000

Data Index: 1142161 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.3097. Min Act: -0.0000

Data Index: 965364 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.3318. Min Act: -0.0000

Data Index: 314980 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.4521. Min Act: -0.0000

Data Index: 325295 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 4.8531. Min Range: -4.8531

Max Act: 4.4488. Min Act: -0.0000

Data Index: 77544 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.8556. Min Act: -0.0000

Data Index: 667883 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.9846. Min Act: -0.0000

Data Index: 489919 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.5896. Min Act: -0.0000

Data Index: 395355 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.7315. Min Act: -0.0000

Data Index: 98055 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.8845. Min Act: -0.0000

Data Index: 1201890 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.6574. Min Act: -0.0000

Data Index: 310771 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 4.8531. Min Range: -4.8531

Max Act: 3.8306. Min Act: -0.0000

Data Index: 14168 (C4 (Web Text))

Max Activating Token Index: 970