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

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

Neuron 178 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: 9.1121. Min Range: -9.1121

Max Act: 9.1121. Min Act: -0.0000

Data Index: 451504 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 9.1121. Min Range: -9.1121

Max Act: 8.7565. Min Act: -0.0000

Data Index: 1246968 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 9.1121. Min Range: -9.1121

Max Act: 8.2628. Min Act: -0.0000

Data Index: 236680 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 9.1121. Min Range: -9.1121

Max Act: 8.3470. Min Act: -0.0000

Data Index: 1254459 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.8803. Min Act: -0.0000

Data Index: 197357 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 9.1121. Min Range: -9.1121

Max Act: 8.2786. Min Act: -0.0000

Data Index: 1300868 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.8586. Min Act: -0.0000

Data Index: 290825 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.9880. Min Act: -0.0000

Data Index: 1100029 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.1427. Min Act: -0.0000

Data Index: 130450 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.5832. Min Act: -0.0000

Data Index: 406710 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.3554. Min Act: -0.0001

Data Index: 612850 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.4830. Min Act: -0.0000

Data Index: 130920 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.7787. Min Act: -0.0000

Data Index: 1023301 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.6825. Min Act: -0.0000

Data Index: 1042668 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.5273. Min Act: -0.0000

Data Index: 1075012 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.0962. Min Act: -0.0000

Data Index: 1277568 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.0690. Min Act: -0.0000

Data Index: 850218 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 9.1121. Min Range: -9.1121

Max Act: 6.7937. Min Act: -0.0000

Data Index: 1092876 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.6678. Min Act: -0.0000

Data Index: 694582 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 9.1121. Min Range: -9.1121

Max Act: 7.2916. Min Act: -0.0000

Data Index: 1121638 (C4 (Web Text))

Max Activating Token Index: 327