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

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

Neuron 3612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1564570 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1565477 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1561745 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8331. Min Act: -0.0001

Data Index: 1651621 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1610557 (Python Code)

Max Activating Token Index: 416

Text #5

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1478832 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1415962 (Python Code)

Max Activating Token Index: 165

Text #7

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1363914 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1438167 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1422385 (Python Code)

Max Activating Token Index: 901

Text #10

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7825. Min Act: -0.0001

Data Index: 1636899 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1407827 (Python Code)

Max Activating Token Index: 196

Text #12

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1628878 (Python Code)

Max Activating Token Index: 486

Text #13

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1520248 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1399142 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1518175 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1527795 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1542314 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1450702 (Python Code)

Max Activating Token Index: 381

Text #19

Max Range: 0.9188. Min Range: -0.9188

Max Act: 0.8550. Min Act: -0.0001

Data Index: 1544810 (Python Code)

Max Activating Token Index: 357