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

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

Neuron 61 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.6577. Min Act: -0.0001

Data Index: 1445079 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.6079. Min Act: -0.0001

Data Index: 1647543 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.4508. Min Act: -0.0001

Data Index: 1381397 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.4021. Min Act: -0.0001

Data Index: 1650329 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.4400. Min Act: -0.0001

Data Index: 1405829 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3916. Min Act: -0.0001

Data Index: 1492607 (Python Code)

Max Activating Token Index: 639

Text #6

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3475. Min Act: -0.0001

Data Index: 1608537 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1509819 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3328. Min Act: -0.0001

Data Index: 1644782 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1388883 (Python Code)

Max Activating Token Index: 846

Text #10

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3572. Min Act: -0.0001

Data Index: 1532143 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1406436 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3472. Min Act: -0.0001

Data Index: 1577475 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3027. Min Act: -0.0001

Data Index: 1492967 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2960. Min Act: -0.0001

Data Index: 1525201 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1525016 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2820. Min Act: -0.0001

Data Index: 1459929 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.3074. Min Act: -0.0000

Data Index: 1635607 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1462232 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 1.6577. Min Range: -1.6577

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1371186 (Python Code)

Max Activating Token Index: 341