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

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

Neuron 1534 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.7082. Min Act: -0.0000

Data Index: 249716 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1423087 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4631. Min Act: -0.0000

Data Index: 601546 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1012853 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2518. Min Act: -0.0000

Data Index: 866215 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1506382 (Python Code)

Max Activating Token Index: 811

Text #6

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2989. Min Act: -0.0000

Data Index: 1434410 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1582635 (Python Code)

Max Activating Token Index: 862

Text #8

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4255. Min Act: -0.0000

Data Index: 1415503 (Python Code)

Max Activating Token Index: 451

Text #9

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4063. Min Act: -0.0000

Data Index: 1217183 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1585721 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4718. Min Act: -0.0000

Data Index: 1432612 (Python Code)

Max Activating Token Index: 969

Text #12

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3470. Min Act: -0.0000

Data Index: 478370 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.3330. Min Act: -0.0000

Data Index: 213884 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.4705. Min Act: -0.0000

Data Index: 1468682 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1570510 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2183. Min Act: -0.0000

Data Index: 1568206 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2012. Min Act: -0.0000

Data Index: 379531 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1615932 (Python Code)

Max Activating Token Index: 577

Text #19

Max Range: 1.7082. Min Range: -1.7082

Max Act: 1.1396. Min Act: -0.0000

Data Index: 343832 (C4 (Web Text))

Max Activating Token Index: 412