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

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

Neuron 2677 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: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.0000

Data Index: 1312724 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.6178. Min Act: -0.0000

Data Index: 1624867 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.4754. Min Act: -0.0000

Data Index: 1465267 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.5700. Min Act: -0.0000

Data Index: 1497334 (Python Code)

Max Activating Token Index: 926

Text #4

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.0853. Min Act: -0.0000

Data Index: 1435130 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.0947. Min Act: -0.0000

Data Index: 216329 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.9516. Min Act: -0.0000

Data Index: 1556199 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.8948. Min Act: -0.0000

Data Index: 1466372 (Python Code)

Max Activating Token Index: 738

Text #8

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.9769. Min Act: -0.0000

Data Index: 480971 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1473092 (Python Code)

Max Activating Token Index: 727

Text #10

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.8426. Min Act: -0.0000

Data Index: 836852 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.0409. Min Act: -0.0000

Data Index: 636115 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 3.6670. Min Range: -3.6670

Max Act: 2.1190. Min Act: -0.0000

Data Index: 1411671 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1313456 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.8822. Min Act: -0.0000

Data Index: 1396415 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.7824. Min Act: -0.0000

Data Index: 1426349 (Python Code)

Max Activating Token Index: 710

Text #16

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.9583. Min Act: -0.0000

Data Index: 243083 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.7235. Min Act: -0.0000

Data Index: 125018 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.7971. Min Act: -0.0000

Data Index: 1452377 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 3.6670. Min Range: -3.6670

Max Act: 1.6879. Min Act: -0.0000

Data Index: 1290618 (C4 (Web Text))

Max Activating Token Index: 388