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

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

Neuron 4698 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1382312 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1361878 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1140560 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6999. Min Act: -0.0000

Data Index: 121132 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1343566 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1534026 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1632988 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1572460 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1493284 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1205542 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6575. Min Act: -0.0000

Data Index: 801845 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1391826 (Python Code)

Max Activating Token Index: 809

Text #12

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5730. Min Act: -0.0000

Data Index: 550226 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1610461 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1320480 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1092288 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1234057 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1006267 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5811. Min Act: -0.0000

Data Index: 902613 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.9435. Min Range: -0.9435

Max Act: 0.5458. Min Act: -0.0000

Data Index: 641836 (C4 (Web Text))

Max Activating Token Index: 270