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

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

Neuron 4342 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: 6.5829. Min Range: -6.5829

Max Act: 6.5829. Min Act: -0.0000

Data Index: 618477 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 6.5829. Min Range: -6.5829

Max Act: 6.5275. Min Act: -0.0000

Data Index: 920352 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 6.5829. Min Range: -6.5829

Max Act: 6.0277. Min Act: -0.0000

Data Index: 656098 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 6.5829. Min Range: -6.5829

Max Act: 5.4177. Min Act: -0.0000

Data Index: 5935 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 6.5829. Min Range: -6.5829

Max Act: 5.3111. Min Act: -0.0000

Data Index: 125011 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 6.5829. Min Range: -6.5829

Max Act: 5.0917. Min Act: -0.0000

Data Index: 1190344 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.8000. Min Act: -0.0000

Data Index: 270450 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.9999. Min Act: -0.0000

Data Index: 876913 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.7448. Min Act: 0.0000

Data Index: 1270673 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.8933. Min Act: -0.0000

Data Index: 37183 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.6892. Min Act: -0.0000

Data Index: 108864 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.6605. Min Act: -0.0000

Data Index: 433202 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.1335. Min Act: -0.0000

Data Index: 109267 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.0872. Min Act: -0.0000

Data Index: 917372 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.3656. Min Act: -0.0000

Data Index: 1302344 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 6.5829. Min Range: -6.5829

Max Act: 4.1180. Min Act: -0.0000

Data Index: 1070424 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 6.5829. Min Range: -6.5829

Max Act: 3.8536. Min Act: -0.0000

Data Index: 772551 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 6.5829. Min Range: -6.5829

Max Act: 3.8057. Min Act: -0.0000

Data Index: 447765 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 6.5829. Min Range: -6.5829

Max Act: 3.9425. Min Act: -0.0000

Data Index: 237344 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 6.5829. Min Range: -6.5829

Max Act: 3.8042. Min Act: -0.0000

Data Index: 697581 (C4 (Web Text))

Max Activating Token Index: 290