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

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

Neuron 1675 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1647495 (Python Code)

Max Activating Token Index: 308

Text #1

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1393334 (Python Code)

Max Activating Token Index: 140

Text #2

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1420459 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1279959 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1362193 (Python Code)

Max Activating Token Index: 434

Text #5

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1448917 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0807. Min Act: -0.0001

Data Index: 487053 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1372163 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0930. Min Act: -0.0000

Data Index: 1599959 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1509183 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1600878 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1560065 (Python Code)

Max Activating Token Index: 829

Text #12

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0859. Min Act: -0.0001

Data Index: 997375 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0853. Min Act: -0.0001

Data Index: 75387 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1438749 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0787. Min Act: -0.0001

Data Index: 375789 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0859. Min Act: -0.0001

Data Index: 501520 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1352817 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0804. Min Act: -0.0001

Data Index: 398638 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.1084. Min Range: -0.1084

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1626359 (Python Code)

Max Activating Token Index: 457