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

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

Neuron 1206 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1534. Min Range: -4.1534

Max Act: 4.1534. Min Act: -0.0001

Data Index: 1354456 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 4.1534. Min Range: -4.1534

Max Act: 4.1534. Min Act: -0.0001

Data Index: 1236544 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.9089. Min Act: -0.0000

Data Index: 796813 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.8598. Min Act: -0.0000

Data Index: 95621 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.6727. Min Act: -0.0001

Data Index: 620137 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.5945. Min Act: -0.0000

Data Index: 238830 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.6014. Min Act: -0.0001

Data Index: 214308 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.4938. Min Act: -0.0000

Data Index: 430147 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.5785. Min Act: -0.0001

Data Index: 703245 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.2039. Min Act: -0.0001

Data Index: 1220370 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.3761. Min Act: -0.0001

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.1974. Min Act: -0.0001

Data Index: 204786 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.2947. Min Act: -0.0000

Data Index: 1013915 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.2978. Min Act: -0.0000

Data Index: 653532 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.3777. Min Act: -0.0001

Data Index: 1347336 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.9763. Min Act: -0.0001

Data Index: 490681 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.0607. Min Act: -0.0001

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.2351. Min Act: -0.0001

Data Index: 558450 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 4.1534. Min Range: -4.1534

Max Act: 2.9234. Min Act: -0.0000

Data Index: 465922 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 4.1534. Min Range: -4.1534

Max Act: 3.1925. Min Act: -0.0000

Data Index: 1076899 (C4 (Web Text))

Max Activating Token Index: 810