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

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

Neuron 3124 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: 1.3303. Min Range: -1.3303

Max Act: 1.3303. Min Act: -0.0000

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.3303. Min Range: -1.3303

Max Act: 1.0031. Min Act: -0.0000

Data Index: 626145 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1414664 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.9306. Min Act: -0.0000

Data Index: 406371 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.8408. Min Act: -0.0000

Data Index: 141144 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.8358. Min Act: -0.0000

Data Index: 585756 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1466945 (Python Code)

Max Activating Token Index: 787

Text #7

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1377903 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1496019 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1650998 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7742. Min Act: -0.0000

Data Index: 507 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7616. Min Act: -0.0000

Data Index: 677262 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1426655 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1028102 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1577977 (Python Code)

Max Activating Token Index: 757

Text #15

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1632978 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7269. Min Act: -0.0000

Data Index: 898644 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7455. Min Act: -0.0000

Data Index: 224988 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7402. Min Act: -0.0000

Data Index: 374022 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.3303. Min Range: -1.3303

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1555917 (Python Code)

Max Activating Token Index: 466