Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.5401. Min Act: -0.0000

Data Index: 347557 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.7143. Min Act: -0.0000

Data Index: 1404856 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2033. Min Act: -0.0000

Data Index: 1639120 (Python Code)

Max Activating Token Index: 829

Text #3

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.4226. Min Act: -0.0000

Data Index: 87065 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2766. Min Act: -0.0000

Data Index: 1032018 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.3368. Min Act: -0.0000

Data Index: 1437396 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1009. Min Act: -0.0000

Data Index: 1389487 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0075. Min Act: -0.0000

Data Index: 1601415 (Python Code)

Max Activating Token Index: 442

Text #8

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1082. Min Act: -0.0000

Data Index: 461787 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1574159 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.2087. Min Act: -0.0000

Data Index: 1368786 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0661. Min Act: -0.0000

Data Index: 1251573 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.1437. Min Act: -0.0000

Data Index: 1610249 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 2.7143. Min Range: -2.7143

Max Act: 1.9407. Min Act: -0.0000

Data Index: 1401202 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 2.7143. Min Range: -2.7143

Max Act: 1.8781. Min Act: -0.0000

Data Index: 298512 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0507. Min Act: -0.0000

Data Index: 1585651 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 2.7143. Min Range: -2.7143

Max Act: 1.9843. Min Act: -0.0000

Data Index: 1397578 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 2.7143. Min Range: -2.7143

Max Act: 1.8002. Min Act: -0.0000

Data Index: 200156 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0083. Min Act: -0.0000

Data Index: 1465787 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 2.7143. Min Range: -2.7143

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1642136 (Python Code)

Max Activating Token Index: 754