Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.8042. Min Act: -0.0001

Data Index: 1479937 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1368768 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1425995 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7150. Min Act: -0.0001

Data Index: 1557682 (Python Code)

Max Activating Token Index: 169

Text #4

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7298. Min Act: -0.0001

Data Index: 1360313 (Python Code)

Max Activating Token Index: 416

Text #5

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1478593 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1423071 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7337. Min Act: -0.0001

Data Index: 1408378 (Python Code)

Max Activating Token Index: 276

Text #8

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1604004 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1442325 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1504985 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6801. Min Act: -0.0001

Data Index: 1463905 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1364404 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1415946 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1475546 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1621878 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1458313 (Python Code)

Max Activating Token Index: 443

Text #17

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.7117. Min Act: -0.0001

Data Index: 1454494 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6277. Min Act: -0.0001

Data Index: 1381593 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1602433 (Python Code)

Max Activating Token Index: 231