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

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

Neuron 1067 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: 5.7568. Min Range: -5.7568

Max Act: 5.7568. Min Act: -0.0000

Data Index: 1320803 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.7568. Min Range: -5.7568

Max Act: 5.1056. Min Act: -0.0000

Data Index: 93805 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 5.7568. Min Range: -5.7568

Max Act: 5.1505. Min Act: -0.0000

Data Index: 971262 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 5.7568. Min Range: -5.7568

Max Act: 4.1957. Min Act: -0.0000

Data Index: 400991 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 5.7568. Min Range: -5.7568

Max Act: 5.2249. Min Act: -0.0000

Data Index: 523388 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 5.7568. Min Range: -5.7568

Max Act: 4.4257. Min Act: -0.0000

Data Index: 774671 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 5.7568. Min Range: -5.7568

Max Act: 4.3829. Min Act: -0.0000

Data Index: 702742 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 5.7568. Min Range: -5.7568

Max Act: 4.1353. Min Act: -0.0000

Data Index: 1274250 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 5.7568. Min Range: -5.7568

Max Act: 4.3608. Min Act: -0.0000

Data Index: 557467 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.9946. Min Act: -0.0000

Data Index: 117990 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.4889. Min Act: -0.0000

Data Index: 1268043 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.9945. Min Act: -0.0000

Data Index: 504872 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.5889. Min Act: -0.0000

Data Index: 1359093 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.4617. Min Act: -0.0000

Data Index: 907148 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.5105. Min Act: -0.0000

Data Index: 75913 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.4971. Min Act: -0.0000

Data Index: 1119968 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.7733. Min Act: 0.0000

Data Index: 387639 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.4192. Min Act: -0.0000

Data Index: 561745 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.5608. Min Act: -0.0000

Data Index: 693562 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 5.7568. Min Range: -5.7568

Max Act: 3.4545. Min Act: -0.0000

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 360