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

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

Neuron 5347 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1387691 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1498360 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1515186 (Python Code)

Max Activating Token Index: 69

Text #3

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5739. Min Act: -0.0000

Data Index: 1573243 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1430880 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4978. Min Act: -0.0000

Data Index: 778903 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5074. Min Act: -0.0000

Data Index: 1548962 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1499743 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5001. Min Act: -0.0000

Data Index: 1524676 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5060. Min Act: -0.0000

Data Index: 1472929 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1594199 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1376881 (Python Code)

Max Activating Token Index: 211

Text #12

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4903. Min Act: -0.0000

Data Index: 28900 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1506664 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1426681 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1475365 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4246. Min Act: -0.0000

Data Index: 1543373 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1618051 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1389536 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 1.7426. Min Range: -1.7426

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1436227 (Python Code)

Max Activating Token Index: 69