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

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

Neuron 1360 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0549. Min Range: -7.0549

Max Act: 7.0549. Min Act: -0.0001

Data Index: 776383 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 7.0549. Min Range: -7.0549

Max Act: 5.7462. Min Act: -0.0000

Data Index: 33968 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 7.0549. Min Range: -7.0549

Max Act: 5.2207. Min Act: -0.0000

Data Index: 1015169 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.7914. Min Act: -0.0000

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.8692. Min Act: -0.0000

Data Index: 680081 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.5959. Min Act: -0.0000

Data Index: 256378 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 7.0549. Min Range: -7.0549

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1227641 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.6679. Min Act: -0.0000

Data Index: 1269833 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.6571. Min Act: -0.0000

Data Index: 281376 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.7712. Min Act: -0.0000

Data Index: 1253429 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.4796. Min Act: -0.0000

Data Index: 240432 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.6090. Min Act: -0.0000

Data Index: 1005635 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.5834. Min Act: -0.0000

Data Index: 1145535 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.5863. Min Act: -0.0000

Data Index: 1085718 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.2004. Min Act: -0.0000

Data Index: 392959 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.5901. Min Act: -0.0000

Data Index: 230399 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.2169. Min Act: -0.0000

Data Index: 565976 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.5541. Min Act: -0.0000

Data Index: 540774 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.8276. Min Act: -0.0000

Data Index: 1123430 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 7.0549. Min Range: -7.0549

Max Act: 2.3132. Min Act: -0.0000

Data Index: 279600 (C4 (Web Text))

Max Activating Token Index: 653