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

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

Neuron 872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0566. Min Range: -7.0566

Max Act: 7.0566. Min Act: -0.0000

Data Index: 304413 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 7.0566. Min Range: -7.0566

Max Act: 6.7910. Min Act: -0.0000

Data Index: 163968 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.8930. Min Act: -0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.6982. Min Act: -0.0000

Data Index: 16990 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.6827. Min Act: -0.0000

Data Index: 583256 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.6574. Min Act: -0.0000

Data Index: 1343750 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.5078. Min Act: -0.0000

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.5054. Min Act: -0.0000

Data Index: 649862 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.3948. Min Act: -0.0000

Data Index: 1235768 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.2104. Min Act: -0.0000

Data Index: 84939 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.3290. Min Act: -0.0000

Data Index: 1079509 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.1684. Min Act: -0.0000

Data Index: 938662 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.3004. Min Act: -0.0000

Data Index: 674453 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.1044. Min Act: -0.0000

Data Index: 190818 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.2505. Min Act: -0.0000

Data Index: 1091305 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.0187. Min Act: -0.0000

Data Index: 404762 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.1560. Min Act: -0.0000

Data Index: 1282350 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.3339. Min Act: -0.0000

Data Index: 940918 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 7.0566. Min Range: -7.0566

Max Act: 5.1070. Min Act: -0.0000

Data Index: 916252 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 7.0566. Min Range: -7.0566

Max Act: 4.9013. Min Act: -0.0000

Data Index: 170903 (C4 (Web Text))

Max Activating Token Index: 599