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

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

Neuron 5201 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: 3.0667. Min Range: -3.0667

Max Act: 3.0667. Min Act: -0.0000

Data Index: 1374005 (Python Code)

Max Activating Token Index: 456

Text #1

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.9731. Min Act: -0.0000

Data Index: 1400129 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.8300. Min Act: -0.0000

Data Index: 1364946 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.8273. Min Act: -0.0000

Data Index: 1552408 (Python Code)

Max Activating Token Index: 489

Text #4

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6783. Min Act: -0.0000

Data Index: 1400460 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.9582. Min Act: -0.0000

Data Index: 1499032 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.7215. Min Act: -0.0000

Data Index: 1534610 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6688. Min Act: -0.0000

Data Index: 1504294 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6104. Min Act: -0.0000

Data Index: 1575639 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.5430. Min Act: -0.0000

Data Index: 1635418 (Python Code)

Max Activating Token Index: 158

Text #10

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.6654. Min Act: -0.0000

Data Index: 1413718 (Python Code)

Max Activating Token Index: 951

Text #11

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.5136. Min Act: -0.0000

Data Index: 1390017 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.4975. Min Act: -0.0000

Data Index: 1571259 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.4842. Min Act: -0.0000

Data Index: 1504922 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1502004 (Python Code)

Max Activating Token Index: 230

Text #15

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.3147. Min Act: -0.0000

Data Index: 1450507 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1438512 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.2786. Min Act: -0.0000

Data Index: 1376580 (Python Code)

Max Activating Token Index: 712

Text #18

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.2617. Min Act: -0.0000

Data Index: 1471811 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 3.0667. Min Range: -3.0667

Max Act: 2.1306. Min Act: -0.0000

Data Index: 1655256 (Python Code)

Max Activating Token Index: 721