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

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

Neuron 5315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0947. Min Range: -4.0947

Max Act: 4.0947. Min Act: -0.0000

Data Index: 402047 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 4.0947. Min Range: -4.0947

Max Act: 3.5662. Min Act: -0.0000

Data Index: 862069 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 4.0947. Min Range: -4.0947

Max Act: 3.2911. Min Act: -0.0000

Data Index: 177658 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 4.0947. Min Range: -4.0947

Max Act: 3.1978. Min Act: -0.0000

Data Index: 575187 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 4.0947. Min Range: -4.0947

Max Act: 3.1369. Min Act: -0.0000

Data Index: 527890 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.8742. Min Act: -0.0000

Data Index: 180918 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.8673. Min Act: -0.0000

Data Index: 69223 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6745. Min Act: -0.0000

Data Index: 929484 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.7960. Min Act: -0.0000

Data Index: 582548 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6465. Min Act: -0.0000

Data Index: 375514 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.7770. Min Act: -0.0000

Data Index: 715349 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.7626. Min Act: -0.0000

Data Index: 317626 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1289137 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.5566. Min Act: -0.0000

Data Index: 549848 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6551. Min Act: -0.0000

Data Index: 282560 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6738. Min Act: -0.0000

Data Index: 1130665 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6321. Min Act: -0.0000

Data Index: 50377 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.3886. Min Act: -0.0000

Data Index: 141668 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.6128. Min Act: -0.0000

Data Index: 344305 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 4.0947. Min Range: -4.0947

Max Act: 2.5897. Min Act: -0.0000

Data Index: 1076792 (C4 (Web Text))

Max Activating Token Index: 489