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

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

Neuron 3619 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.3270. Min Act: -0.0000

Data Index: 1428592 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.3923. Min Act: -0.0000

Data Index: 1524437 (Python Code)

Max Activating Token Index: 553

Text #2

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.3953. Min Act: -0.0000

Data Index: 1655791 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.3301. Min Act: -0.0000

Data Index: 1503414 (Python Code)

Max Activating Token Index: 587

Text #4

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.3367. Min Act: -0.0000

Data Index: 1569267 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1533346 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1448969 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1440364 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1495546 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1631347 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1254. Min Act: -0.0000

Data Index: 1427032 (Python Code)

Max Activating Token Index: 385

Text #11

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1542. Min Act: -0.0000

Data Index: 1587996 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.0509. Min Act: -0.0000

Data Index: 1421693 (Python Code)

Max Activating Token Index: 851

Text #13

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1193. Min Act: -0.0000

Data Index: 1597385 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 2.3953. Min Range: -2.3953

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1459609 (Python Code)

Max Activating Token Index: 751

Text #15

Max Range: 2.3953. Min Range: -2.3953

Max Act: 1.8616. Min Act: -0.0000

Data Index: 1587699 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 2.3953. Min Range: -2.3953

Max Act: 1.9855. Min Act: -0.0000

Data Index: 1519516 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 2.3953. Min Range: -2.3953

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1407652 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.0735. Min Act: -0.0000

Data Index: 1485231 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 2.3953. Min Range: -2.3953

Max Act: 2.1755. Min Act: -0.0000

Data Index: 1498229 (Python Code)

Max Activating Token Index: 325