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

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

Neuron 3135 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7965. Min Act: -0.0000

Data Index: 193981 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1147428 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7719. Min Act: -0.0000

Data Index: 57634 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1350982 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.8612. Min Act: -0.0000

Data Index: 282643 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1485561 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1171233 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6743. Min Act: -0.0000

Data Index: 643874 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7094. Min Act: -0.0001

Data Index: 1379165 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1499229 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6854. Min Act: -0.0000

Data Index: 752655 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6073. Min Act: -0.0001

Data Index: 1516949 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1387486 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6338. Min Act: -0.0000

Data Index: 702823 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.7102. Min Act: -0.0000

Data Index: 723939 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6590. Min Act: -0.0001

Data Index: 1513720 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6250. Min Act: -0.0001

Data Index: 1645556 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6821. Min Act: -0.0001

Data Index: 1557029 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1566104 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.8612. Min Range: -0.8612

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1408967 (Python Code)

Max Activating Token Index: 574