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

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

Neuron 641 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: 2.6416. Min Range: -2.6416

Max Act: 2.6416. Min Act: -0.0000

Data Index: 1465346 (Python Code)

Max Activating Token Index: 172

Text #1

Max Range: 2.6416. Min Range: -2.6416

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1645632 (Python Code)

Max Activating Token Index: 187

Text #2

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1654303 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.6316. Min Act: -0.0000

Data Index: 1399888 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5846. Min Act: -0.0000

Data Index: 1618603 (Python Code)

Max Activating Token Index: 349

Text #5

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1529765 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1483549 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1635344 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.5133. Min Act: -0.0000

Data Index: 1447566 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4999. Min Act: -0.0000

Data Index: 1367503 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1632668 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1547884 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1538281 (Python Code)

Max Activating Token Index: 638

Text #13

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1510820 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1504210 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1542933 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1627170 (Python Code)

Max Activating Token Index: 395

Text #17

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1523351 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.2741. Min Act: -0.0000

Data Index: 1499194 (Python Code)

Max Activating Token Index: 751

Text #19

Max Range: 2.6416. Min Range: -2.6416

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1588762 (Python Code)

Max Activating Token Index: 473