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

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

Neuron 5218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.4369. Min Act: -0.0000

Data Index: 1500796 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.4679. Min Act: -0.0000

Data Index: 1495521 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.9497. Min Act: -0.0000

Data Index: 1383363 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.4076. Min Act: -0.0000

Data Index: 1648834 (Python Code)

Max Activating Token Index: 355

Text #4

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.2650. Min Act: -0.0000

Data Index: 1419053 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.3306. Min Act: -0.0000

Data Index: 1566950 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 2.9497. Min Range: -2.9497

Max Act: 1.7041. Min Act: -0.0000

Data Index: 1643418 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.1200. Min Act: -0.0000

Data Index: 1568277 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.4876. Min Act: -0.0000

Data Index: 1485364 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.2379. Min Act: -0.0000

Data Index: 1435116 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 2.9497. Min Range: -2.9497

Max Act: 1.8420. Min Act: -0.0000

Data Index: 1492680 (Python Code)

Max Activating Token Index: 702

Text #11

Max Range: 2.9497. Min Range: -2.9497

Max Act: 1.7477. Min Act: -0.0000

Data Index: 1575374 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.2103. Min Act: -0.0000

Data Index: 1434187 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.1615. Min Act: -0.0000

Data Index: 1380200 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.4875. Min Act: -0.0000

Data Index: 1553420 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.1440. Min Act: -0.0000

Data Index: 1627920 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.2645. Min Act: -0.0000

Data Index: 1457103 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.0647. Min Act: -0.0000

Data Index: 1564868 (Python Code)

Max Activating Token Index: 93

Text #18

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1373077 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 2.9497. Min Range: -2.9497

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1564046 (Python Code)

Max Activating Token Index: 273