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

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

Neuron 2675 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6405. Min Range: -3.6405

Max Act: 3.6405. Min Act: -0.0000

Data Index: 1266555 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 3.6405. Min Range: -3.6405

Max Act: 3.4251. Min Act: -0.0000

Data Index: 202133 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 3.6405. Min Range: -3.6405

Max Act: 3.4467. Min Act: -0.0000

Data Index: 507261 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.8534. Min Act: -0.0000

Data Index: 810693 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.9593. Min Act: -0.0000

Data Index: 131571 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.8707. Min Act: -0.0000

Data Index: 158723 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.6665. Min Act: -0.0000

Data Index: 768279 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.4889. Min Act: -0.0000

Data Index: 1174847 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.6405. Min Range: -3.6405

Max Act: 2.4078. Min Act: -0.0000

Data Index: 591830 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.9680. Min Act: -0.0000

Data Index: 823349 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1061384 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.6795. Min Act: -0.0000

Data Index: 868873 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.8082. Min Act: -0.0000

Data Index: 244735 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.6564. Min Act: -0.0000

Data Index: 216481 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.5905. Min Act: -0.0000

Data Index: 922116 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.5614. Min Act: -0.0000

Data Index: 719603 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.6005. Min Act: -0.0000

Data Index: 147951 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.4283. Min Act: -0.0000

Data Index: 996924 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.6924. Min Act: -0.0000

Data Index: 258510 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.6405. Min Range: -3.6405

Max Act: 1.5579. Min Act: -0.0000

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 958