Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3964 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1451681 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4731. Min Act: -0.0001

Data Index: 1373292 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1656319 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4719. Min Act: -0.0001

Data Index: 1513539 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3604. Min Act: -0.0001

Data Index: 1430910 (Python Code)

Max Activating Token Index: 597

Text #5

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.4195. Min Act: -0.0001

Data Index: 1413659 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3248. Min Act: -0.0001

Data Index: 1464487 (Python Code)

Max Activating Token Index: 800

Text #7

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3601. Min Act: -0.0001

Data Index: 1446775 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1636211 (Python Code)

Max Activating Token Index: 877

Text #9

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1500933 (Python Code)

Max Activating Token Index: 733

Text #10

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3430. Min Act: -0.0001

Data Index: 1488610 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3303. Min Act: -0.0001

Data Index: 1381090 (Python Code)

Max Activating Token Index: 260

Text #12

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2380. Min Act: -0.0001

Data Index: 1369626 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2097. Min Act: -0.0001

Data Index: 1436589 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2291. Min Act: -0.0001

Data Index: 1363985 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2994. Min Act: -0.0001

Data Index: 1570934 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2911. Min Act: -0.0001

Data Index: 1500004 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.3086. Min Act: -0.0001

Data Index: 1591130 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.2748. Min Act: -0.0001

Data Index: 1623758 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 1.4731. Min Range: -1.4731

Max Act: 1.1782. Min Act: -0.0001

Data Index: 1453979 (Python Code)

Max Activating Token Index: 705