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

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

Neuron 1563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5175. Min Range: -2.5175

Max Act: 2.5175. Min Act: -0.0000

Data Index: 1471704 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 2.5175. Min Range: -2.5175

Max Act: 2.2620. Min Act: -0.0000

Data Index: 1534312 (Python Code)

Max Activating Token Index: 318

Text #2

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.9361. Min Act: -0.0000

Data Index: 1140141 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.5175. Min Range: -2.5175

Max Act: 2.1620. Min Act: -0.0000

Data Index: 860757 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.9170. Min Act: -0.0000

Data Index: 219920 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1626656 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.7717. Min Act: -0.0000

Data Index: 18229 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1567157 (Python Code)

Max Activating Token Index: 555

Text #8

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.7536. Min Act: -0.0000

Data Index: 1447103 (Python Code)

Max Activating Token Index: 63

Text #9

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1478843 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1546013 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1144714 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6859. Min Act: -0.0000

Data Index: 366546 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6333. Min Act: -0.0000

Data Index: 174304 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6281. Min Act: -0.0000

Data Index: 10454 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.7022. Min Act: -0.0000

Data Index: 1320830 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1380658 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6152. Min Act: -0.0000

Data Index: 310082 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.6022. Min Act: -0.0000

Data Index: 1438633 (Python Code)

Max Activating Token Index: 226

Text #19

Max Range: 2.5175. Min Range: -2.5175

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1634867 (Python Code)

Max Activating Token Index: 344