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

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

Neuron 63 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9120. Min Act: -0.0000

Data Index: 1369028 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1363241 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1599954 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1480709 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1561189 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1507230 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1611946 (Python Code)

Max Activating Token Index: 162

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1397158 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7007. Min Act: -0.0000

Data Index: 679818 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1425938 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1360625 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1632952 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7136. Min Act: -0.0000

Data Index: 609124 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7349. Min Act: -0.0000

Data Index: 444374 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1535913 (Python Code)

Max Activating Token Index: 621

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1401081 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1597818 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1541478 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1377480 (Python Code)

Max Activating Token Index: 952

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1644731 (Python Code)

Max Activating Token Index: 943