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

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

Neuron 21 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1651788 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1403644 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1588659 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1399040 (Python Code)

Max Activating Token Index: 471

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1413119 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1611211 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1502465 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1492701 (Python Code)

Max Activating Token Index: 688

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1106022 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1609237 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1584108 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1543163 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1527739 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1523085 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1539133 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1566967 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1432836 (Python Code)

Max Activating Token Index: 92

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1590303 (Python Code)

Max Activating Token Index: 1006

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1415595 (Python Code)

Max Activating Token Index: 493

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1397062 (Python Code)

Max Activating Token Index: 296