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

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

Neuron 1987 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.4838. Min Act: -0.0000

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3849. Min Act: -0.0000

Data Index: 397053 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3997. Min Act: -0.0000

Data Index: 46297 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3750. Min Act: -0.0000

Data Index: 840514 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1321819 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1603796 (Python Code)

Max Activating Token Index: 840

Text #6

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1593909 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3659. Min Act: -0.0000

Data Index: 546523 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3423. Min Act: -0.0000

Data Index: 211949 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1442390 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3241. Min Act: -0.0000

Data Index: 183711 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3361. Min Act: -0.0000

Data Index: 60062 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1583361 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3295. Min Act: -0.0000

Data Index: 198958 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3411. Min Act: -0.0000

Data Index: 1442889 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1399464 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1048031 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1024044 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1511074 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 0.4838. Min Range: -0.4838

Max Act: 0.2873. Min Act: -0.0000

Data Index: 755363 (C4 (Web Text))

Max Activating Token Index: 974