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

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

Neuron 3241 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1594619 (Python Code)

Max Activating Token Index: 565

Text #1

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.7443. Min Act: -0.0001

Data Index: 1438003 (Python Code)

Max Activating Token Index: 539

Text #2

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.6594. Min Act: -0.0001

Data Index: 1610275 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.7085. Min Act: -0.0001

Data Index: 1497158 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.6102. Min Act: -0.0001

Data Index: 1616739 (Python Code)

Max Activating Token Index: 583

Text #5

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1508123 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5476. Min Act: -0.0001

Data Index: 1416844 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5712. Min Act: -0.0001

Data Index: 1538946 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5682. Min Act: -0.0001

Data Index: 1562141 (Python Code)

Max Activating Token Index: 826

Text #9

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5560. Min Act: -0.0001

Data Index: 1559186 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1574236 (Python Code)

Max Activating Token Index: 435

Text #11

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1510267 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5333. Min Act: -0.0001

Data Index: 1636856 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5372. Min Act: -0.0001

Data Index: 1634924 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1656707 (Python Code)

Max Activating Token Index: 253

Text #15

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1451051 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.4956. Min Act: -0.0001

Data Index: 1518279 (Python Code)

Max Activating Token Index: 462

Text #17

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1440705 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.4800. Min Act: -0.0001

Data Index: 1619917 (Python Code)

Max Activating Token Index: 427

Text #19

Max Range: 0.7755. Min Range: -0.7755

Max Act: 0.4916. Min Act: -0.0000

Data Index: 174962 (C4 (Web Text))

Max Activating Token Index: 221