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

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

Neuron 1870 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: 3.4795. Min Range: -3.4795

Max Act: 3.4795. Min Act: -0.0001

Data Index: 110430 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 3.4795. Min Range: -3.4795

Max Act: 3.1111. Min Act: -0.0001

Data Index: 487530 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 3.4795. Min Range: -3.4795

Max Act: 3.1733. Min Act: -0.0001

Data Index: 255273 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.9992. Min Act: -0.0001

Data Index: 378688 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.5083. Min Act: -0.0001

Data Index: 646010 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.5644. Min Act: -0.0001

Data Index: 1240376 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4419. Min Act: -0.0001

Data Index: 418902 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.1016. Min Act: -0.0001

Data Index: 113525 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4897. Min Act: -0.0000

Data Index: 1386307 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.6157. Min Act: -0.0000

Data Index: 1429001 (Python Code)

Max Activating Token Index: 726

Text #10

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4775. Min Act: -0.0001

Data Index: 600679 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4386. Min Act: -0.0001

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4214. Min Act: -0.0001

Data Index: 134782 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.3879. Min Act: -0.0001

Data Index: 1013035 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.2525. Min Act: -0.0001

Data Index: 318621 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.1247. Min Act: -0.0001

Data Index: 369319 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.3081. Min Act: -0.0001

Data Index: 335230 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.1856. Min Act: -0.0001

Data Index: 121942 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.4038. Min Act: -0.0001

Data Index: 1266691 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.4795. Min Range: -3.4795

Max Act: 2.3685. Min Act: -0.0000

Data Index: 794105 (C4 (Web Text))

Max Activating Token Index: 98