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

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

Neuron 5657 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5853. Min Act: -0.0000

Data Index: 1274611 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4676. Min Act: -0.0000

Data Index: 166675 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3887. Min Act: -0.0000

Data Index: 27470 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3627. Min Act: -0.0000

Data Index: 445844 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.4411. Min Act: 0.0000

Data Index: 153006 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1004046 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.3062. Min Act: -0.0000

Data Index: 144975 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2670. Min Act: -0.0000

Data Index: 41028 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2464. Min Act: -0.0000

Data Index: 831632 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2985. Min Act: -0.0000

Data Index: 136948 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1248929 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0881. Min Act: -0.0000

Data Index: 359907 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0906. Min Act: -0.0000

Data Index: 244246 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1575. Min Act: -0.0000

Data Index: 689596 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1031324 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0965. Min Act: -0.0000

Data Index: 245188 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0945. Min Act: -0.0000

Data Index: 246757 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1317897 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0687. Min Act: -0.0000

Data Index: 181122 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0632. Min Act: -0.0000

Data Index: 963701 (C4 (Web Text))

Max Activating Token Index: 863