Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1610 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1018. Min Range: -1.1018

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1506228 (Python Code)

Max Activating Token Index: 694

Text #1

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1632146 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.1018. Min Range: -1.1018

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1602663 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8488. Min Act: -0.0001

Data Index: 1438575 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1593292 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1126031 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1488771 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1157644 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8471. Min Act: -0.0001

Data Index: 1397800 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8358. Min Act: -0.0000

Data Index: 215734 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.9498. Min Act: -0.0000

Data Index: 718068 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1195453 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8585. Min Act: -0.0000

Data Index: 950812 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.7882. Min Act: -0.0000

Data Index: 682647 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1651532 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1189353 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8468. Min Act: -0.0000

Data Index: 849511 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1580325 (Python Code)

Max Activating Token Index: 801

Text #18

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1411041 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 1.1018. Min Range: -1.1018

Max Act: 0.8602. Min Act: -0.0000

Data Index: 434587 (C4 (Web Text))

Max Activating Token Index: 530