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

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

Neuron 1104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4951. Min Act: -0.0002

Data Index: 1628761 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4697. Min Act: -0.0002

Data Index: 1655780 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5083. Min Act: -0.0002

Data Index: 1510502 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5068. Min Act: -0.0002

Data Index: 1606812 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5080. Min Act: -0.0002

Data Index: 1437991 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4619. Min Act: -0.0002

Data Index: 1587865 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5269. Min Act: -0.0002

Data Index: 1474670 (Python Code)

Max Activating Token Index: 167

Text #7

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5263. Min Act: -0.0002

Data Index: 1598673 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5337. Min Act: -0.0002

Data Index: 1434713 (Python Code)

Max Activating Token Index: 158

Text #9

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5007. Min Act: -0.0002

Data Index: 1379887 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5085. Min Act: -0.0002

Data Index: 1400165 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4572. Min Act: -0.0002

Data Index: 1599799 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4687. Min Act: -0.0002

Data Index: 1456402 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.5279. Min Act: -0.0002

Data Index: 1620185 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4299. Min Act: -0.0002

Data Index: 1476383 (Python Code)

Max Activating Token Index: 263

Text #15

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4297. Min Act: -0.0002

Data Index: 1379628 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4931. Min Act: -0.0002

Data Index: 1480111 (Python Code)

Max Activating Token Index: 670

Text #17

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4281. Min Act: -0.0002

Data Index: 1615959 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4657. Min Act: -0.0002

Data Index: 1612099 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.5337. Min Range: -0.5337

Max Act: 0.4927. Min Act: -0.0002

Data Index: 1434848 (Python Code)

Max Activating Token Index: 435