Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1401001 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1362396 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1539091 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1621999 (Python Code)

Max Activating Token Index: 816

Text #4

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1492225 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7553. Min Act: -0.0001

Data Index: 1486785 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1656382 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1396456 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1590884 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1441997 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1549823 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1443204 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7453. Min Act: -0.0001

Data Index: 1536872 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7417. Min Act: -0.0001

Data Index: 1462074 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7622. Min Act: -0.0001

Data Index: 1563730 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7574. Min Act: -0.0000

Data Index: 1393849 (Python Code)

Max Activating Token Index: 23

Text #16

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7558. Min Act: -0.0001

Data Index: 1364563 (Python Code)

Max Activating Token Index: 68

Text #17

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1401583 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1391249 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.9123. Min Range: -0.9123

Max Act: 0.6948. Min Act: -0.0001

Data Index: 1531340 (Python Code)

Max Activating Token Index: 54