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

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

Neuron 6114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8976. Min Act: -0.0001

Data Index: 188039 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8739. Min Act: -0.0000

Data Index: 12389 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8225. Min Act: -0.0001

Data Index: 1083792 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1131696 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7729. Min Act: -0.0000

Data Index: 903531 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7599. Min Act: -0.0000

Data Index: 724584 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7855. Min Act: -0.0001

Data Index: 141825 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7580. Min Act: -0.0001

Data Index: 555687 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1323082 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7384. Min Act: -0.0001

Data Index: 508057 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1226842 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7542. Min Act: -0.0000

Data Index: 585650 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7520. Min Act: -0.0000

Data Index: 701699 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7804. Min Act: -0.0000

Data Index: 920135 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1029661 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6972. Min Act: -0.0000

Data Index: 42559 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6858. Min Act: -0.0000

Data Index: 166014 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.7318. Min Act: -0.0001

Data Index: 1002539 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1320908 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.8976. Min Range: -0.8976

Max Act: 0.6454. Min Act: -0.0000

Data Index: 128739 (C4 (Web Text))

Max Activating Token Index: 427