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

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

Neuron 5587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.1565. Min Act: -0.0000

Data Index: 112295 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1128974 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.2056. Min Act: -0.0000

Data Index: 895284 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.1015. Min Act: -0.0000

Data Index: 756450 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.1672. Min Act: -0.0000

Data Index: 1025616 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1265745 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.9907. Min Act: -0.0000

Data Index: 523564 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.8691. Min Act: -0.0000

Data Index: 995517 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.8574. Min Act: -0.0000

Data Index: 1201606 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.9521. Min Act: -0.0000

Data Index: 630105 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.2056. Min Range: -2.2056

Max Act: 2.0152. Min Act: -0.0000

Data Index: 486929 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1337833 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7882. Min Act: -0.0000

Data Index: 338433 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.6979. Min Act: -0.0000

Data Index: 122566 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7644. Min Act: -0.0000

Data Index: 532380 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1102454 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1328580 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1062398 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7014. Min Act: -0.0000

Data Index: 1580372 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 2.2056. Min Range: -2.2056

Max Act: 1.7827. Min Act: -0.0000

Data Index: 174584 (C4 (Web Text))

Max Activating Token Index: 1007