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

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

Neuron 539 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: 2.2612. Min Range: -2.2612

Max Act: 2.1916. Min Act: -0.0000

Data Index: 1511233 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.2612. Min Act: -0.0000

Data Index: 1643747 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1987. Min Act: -0.0000

Data Index: 1626332 (Python Code)

Max Activating Token Index: 328

Text #3

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1617. Min Act: -0.0000

Data Index: 1612943 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1688. Min Act: -0.0000

Data Index: 1577539 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1340. Min Act: -0.0000

Data Index: 1508765 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1034. Min Act: -0.0000

Data Index: 1650080 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.1218. Min Act: -0.0000

Data Index: 1485144 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.0946. Min Act: 0.0000

Data Index: 1516403 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.0814. Min Act: -0.0000

Data Index: 1615408 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.0661. Min Act: -0.0000

Data Index: 1439147 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.9543. Min Act: 0.0000

Data Index: 1421542 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.2095. Min Act: -0.0000

Data Index: 1557088 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 2.2612. Min Range: -2.2612

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1535498 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.9049. Min Act: -0.0000

Data Index: 1360272 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.5329. Min Act: -0.0000

Data Index: 1543845 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.8681. Min Act: 0.0000

Data Index: 1587539 (Python Code)

Max Activating Token Index: 111

Text #17

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.9659. Min Act: -0.0000

Data Index: 986119 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.9522. Min Act: -0.0000

Data Index: 1541710 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 2.2612. Min Range: -2.2612

Max Act: 1.9531. Min Act: -0.0000

Data Index: 1533451 (Python Code)

Max Activating Token Index: 127