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

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

Neuron 1689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.6517. Min Act: -0.0001

Data Index: 456922 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3596. Min Act: -0.0001

Data Index: 1297961 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2923. Min Act: -0.0001

Data Index: 86927 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2664. Min Act: -0.0001

Data Index: 166656 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.3546. Min Act: -0.0001

Data Index: 106919 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1736. Min Act: -0.0001

Data Index: 617299 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.2643. Min Act: -0.0001

Data Index: 1175104 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1308. Min Act: -0.0001

Data Index: 104808 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1746. Min Act: -0.0001

Data Index: 967120 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.0780. Min Act: -0.0001

Data Index: 530373 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1209463 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1321. Min Act: -0.0001

Data Index: 626010 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.0907. Min Act: -0.0001

Data Index: 301191 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1000. Min Act: -0.0001

Data Index: 865593 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1851. Min Act: -0.0001

Data Index: 50351 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1187. Min Act: -0.0001

Data Index: 1108624 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.0496. Min Act: -0.0001

Data Index: 1236651 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.1088. Min Act: -0.0001

Data Index: 933144 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.0165. Min Act: -0.0001

Data Index: 224325 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.6517. Min Range: -1.6517

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1522662 (Python Code)

Max Activating Token Index: 148