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

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

Neuron 1816 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: 0.1771. Min Range: -0.1771

Max Act: 0.1771. Min Act: -0.0001

Data Index: 709496 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1602. Min Act: -0.0000

Data Index: 1231332 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1500. Min Act: -0.0001

Data Index: 206977 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1591. Min Act: -0.0001

Data Index: 870848 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1486. Min Act: -0.0001

Data Index: 668640 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1416. Min Act: -0.0001

Data Index: 815264 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1499. Min Act: -0.0001

Data Index: 531254 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1474. Min Act: -0.0001

Data Index: 968752 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1574. Min Act: -0.0001

Data Index: 511624 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1469. Min Act: -0.0001

Data Index: 172908 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1535. Min Act: -0.0001

Data Index: 902304 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1525. Min Act: -0.0001

Data Index: 20239 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1485. Min Act: -0.0001

Data Index: 372563 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1371. Min Act: -0.0001

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1501. Min Act: -0.0001

Data Index: 232800 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1493. Min Act: -0.0001

Data Index: 450590 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1461. Min Act: -0.0001

Data Index: 805603 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1484. Min Act: -0.0001

Data Index: 988750 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1415. Min Act: -0.0001

Data Index: 187276 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.1771. Min Range: -0.1771

Max Act: 0.1368. Min Act: -0.0001

Data Index: 929190 (C4 (Web Text))

Max Activating Token Index: 938