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

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

Neuron 19 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.9835. Min Act: -0.0000

Data Index: 752591 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6185. Min Act: -0.0000

Data Index: 277271 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.6212. Min Act: -0.0000

Data Index: 359369 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.5254. Min Act: -0.0000

Data Index: 355599 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4831. Min Act: -0.0000

Data Index: 569642 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4827. Min Act: -0.0000

Data Index: 1103726 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.4302. Min Act: -0.0000

Data Index: 187298 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3930. Min Act: -0.0000

Data Index: 373534 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1074564 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3424. Min Act: -0.0000

Data Index: 507915 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3451. Min Act: -0.0000

Data Index: 972370 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3398. Min Act: -0.0000

Data Index: 574877 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3158. Min Act: -0.0000

Data Index: 249022 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.3076. Min Act: -0.0000

Data Index: 759829 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1096985 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.2653. Min Act: -0.0000

Data Index: 917492 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1145106 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.1779. Min Act: -0.0000

Data Index: 272534 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.2607. Min Act: -0.0000

Data Index: 204729 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.9835. Min Range: -1.9835

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1007057 (C4 (Web Text))

Max Activating Token Index: 134