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

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

Neuron 3217 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: 0.2937. Min Range: -0.2937

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1207243 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1297297 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2294. Min Act: -0.0000

Data Index: 785248 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2265. Min Act: -0.0000

Data Index: 333188 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1063006 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1100478 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2097. Min Act: -0.0000

Data Index: 197763 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1944. Min Act: -0.0000

Data Index: 894383 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1916. Min Act: -0.0000

Data Index: 757811 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1607054 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1878. Min Act: -0.0000

Data Index: 208187 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1878. Min Act: -0.0000

Data Index: 135332 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1908. Min Act: -0.0000

Data Index: 940174 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1888. Min Act: -0.0000

Data Index: 93130 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1891. Min Act: -0.0000

Data Index: 18606 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1250036 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1335449 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1872. Min Act: -0.0000

Data Index: 608143 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.2937. Min Range: -0.2937

Max Act: 0.1794. Min Act: -0.0000

Data Index: 30403 (C4 (Web Text))

Max Activating Token Index: 276