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

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

Neuron 3004 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: 3.3953. Min Range: -3.3953

Max Act: 3.3953. Min Act: -0.0000

Data Index: 1547419 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1415720 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1517249 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.7480. Min Act: -0.0000

Data Index: 1380256 (Python Code)

Max Activating Token Index: 336

Text #4

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.5816. Min Act: -0.0000

Data Index: 1384757 (Python Code)

Max Activating Token Index: 281

Text #5

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.4359. Min Act: -0.0000

Data Index: 1620967 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.2538. Min Act: -0.0000

Data Index: 1433798 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.3092. Min Act: -0.0000

Data Index: 1474126 (Python Code)

Max Activating Token Index: 482

Text #8

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1504966 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.3813. Min Act: -0.0000

Data Index: 1580466 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.3906. Min Act: -0.0000

Data Index: 1408109 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.1261. Min Act: -0.0000

Data Index: 1448480 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.3030. Min Act: -0.0000

Data Index: 1506611 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.2901. Min Act: -0.0000

Data Index: 1370875 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.1830. Min Act: -0.0000

Data Index: 1383093 (Python Code)

Max Activating Token Index: 449

Text #15

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.0845. Min Act: -0.0000

Data Index: 1378920 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1615678 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 3.3953. Min Range: -3.3953

Max Act: 1.9980. Min Act: -0.0000

Data Index: 1428604 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 3.3953. Min Range: -3.3953

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1543534 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 3.3953. Min Range: -3.3953

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1585314 (Python Code)

Max Activating Token Index: 268