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

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

Neuron 3672 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: 1.9405. Min Range: -1.9405

Max Act: 1.9405. Min Act: -0.0001

Data Index: 1599350 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6160. Min Act: -0.0001

Data Index: 1512694 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.8070. Min Act: -0.0001

Data Index: 1494066 (Python Code)

Max Activating Token Index: 914

Text #3

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7886. Min Act: -0.0001

Data Index: 1003056 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.7281. Min Act: -0.0001

Data Index: 100030 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6195. Min Act: -0.0001

Data Index: 926066 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.5991. Min Act: -0.0001

Data Index: 1446817 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.5774. Min Act: -0.0001

Data Index: 120996 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.5557. Min Act: -0.0001

Data Index: 1559076 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6621. Min Act: -0.0001

Data Index: 388489 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4656. Min Act: -0.0001

Data Index: 1618381 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4847. Min Act: -0.0001

Data Index: 149185 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4692. Min Act: -0.0001

Data Index: 1231579 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4027. Min Act: -0.0001

Data Index: 838832 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4690. Min Act: -0.0001

Data Index: 635799 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4394. Min Act: -0.0001

Data Index: 986358 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4408. Min Act: -0.0001

Data Index: 98766 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.6227. Min Act: -0.0001

Data Index: 913266 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4460. Min Act: -0.0001

Data Index: 1526156 (Python Code)

Max Activating Token Index: 971

Text #19

Max Range: 1.9405. Min Range: -1.9405

Max Act: 1.4576. Min Act: -0.0001

Data Index: 1509517 (Python Code)

Max Activating Token Index: 94