Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 750 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0001

Data Index: 13185 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1182620 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1711. Min Act: -0.0001

Data Index: 173445 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1650. Min Act: -0.0001

Data Index: 329242 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1658. Min Act: -0.0001

Data Index: 623443 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1608. Min Act: -0.0001

Data Index: 67667 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1605. Min Act: -0.0001

Data Index: 343371 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1586. Min Act: -0.0001

Data Index: 691961 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1078373 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1175881 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1530. Min Act: -0.0001

Data Index: 870769 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1466. Min Act: -0.0001

Data Index: 658734 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1270666 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1038300 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1489. Min Act: -0.0001

Data Index: 806000 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1423. Min Act: -0.0001

Data Index: 703952 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1476. Min Act: -0.0001

Data Index: 518393 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1345694 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1382. Min Act: -0.0001

Data Index: 902113 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1436. Min Act: -0.0001

Data Index: 222969 (C4 (Web Text))

Max Activating Token Index: 595