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

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

Neuron 5113 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5356. Min Act: -0.0000

Data Index: 646232 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.7426. Min Act: 0.0000

Data Index: 1622815 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.5507. Min Act: -0.0000

Data Index: 1250676 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.4832. Min Act: -0.0000

Data Index: 1036539 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.3785. Min Act: -0.0000

Data Index: 1447134 (Python Code)

Max Activating Token Index: 824

Text #5

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.3276. Min Act: -0.0000

Data Index: 1473126 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.1749. Min Act: -0.0000

Data Index: 619529 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.3112. Min Act: -0.0000

Data Index: 1073352 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.2602. Min Act: -0.0000

Data Index: 780535 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.2072. Min Act: 0.0000

Data Index: 1435481 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 3.5356. Min Range: -3.5356

Max Act: 2.1863. Min Act: -0.0000

Data Index: 234833 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1531745 (Python Code)

Max Activating Token Index: 156

Text #12

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.9612. Min Act: 0.0000

Data Index: 1625721 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.8385. Min Act: 0.0000

Data Index: 1422524 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1392455 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.6637. Min Act: 0.0000

Data Index: 1644064 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.7351. Min Act: 0.0000

Data Index: 1532040 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.8324. Min Act: 0.0000

Data Index: 1520097 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.7167. Min Act: 0.0001

Data Index: 1589591 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 3.5356. Min Range: -3.5356

Max Act: 1.7522. Min Act: 0.0000

Data Index: 1415664 (Python Code)

Max Activating Token Index: 742