Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3861 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1348147 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5056. Min Act: -0.0000

Data Index: 738762 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4742. Min Act: -0.0000

Data Index: 473243 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4698. Min Act: -0.0000

Data Index: 805150 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4027. Min Act: -0.0000

Data Index: 34629 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1082102 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3830. Min Act: -0.0000

Data Index: 157611 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4079. Min Act: -0.0000

Data Index: 150671 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1272952 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1166746 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3149. Min Act: -0.0000

Data Index: 307193 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3662. Min Act: -0.0000

Data Index: 34771 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3608. Min Act: -0.0000

Data Index: 602030 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3442. Min Act: -0.0000

Data Index: 37260 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3559. Min Act: -0.0000

Data Index: 184815 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3471. Min Act: -0.0000

Data Index: 876485 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3272. Min Act: -0.0000

Data Index: 865484 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3394. Min Act: -0.0000

Data Index: 228020 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3105. Min Act: -0.0000

Data Index: 254895 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1143206 (C4 (Web Text))

Max Activating Token Index: 169