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

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

Neuron 234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: 0.0000

Data Index: 1186991 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1816. Min Act: -0.0000

Data Index: 695254 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1814. Min Act: -0.0000

Data Index: 128220 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1081313 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1738. Min Act: 0.0001

Data Index: 785234 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1610. Min Act: 0.0000

Data Index: 871461 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1711. Min Act: 0.0000

Data Index: 820927 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1590. Min Act: 0.0000

Data Index: 205940 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1353144 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1650. Min Act: 0.0000

Data Index: 44604 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1558. Min Act: -0.0000

Data Index: 292563 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1606. Min Act: -0.0000

Data Index: 364431 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1500. Min Act: -0.0000

Data Index: 834603 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1531. Min Act: 0.0000

Data Index: 1141045 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1466. Min Act: 0.0000

Data Index: 508029 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1586. Min Act: 0.0001

Data Index: 1016553 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1638. Min Act: 0.0000

Data Index: 382952 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1510. Min Act: 0.0000

Data Index: 1250267 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1501. Min Act: -0.0000

Data Index: 991082 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1084712 (C4 (Web Text))

Max Activating Token Index: 176