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

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

Neuron 515 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: 4.7988. Min Range: -4.7988

Max Act: 4.7450. Min Act: -0.0000

Data Index: 556495 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 4.7988. Min Range: -4.7988

Max Act: 4.7988. Min Act: -0.0000

Data Index: 708464 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 4.7988. Min Range: -4.7988

Max Act: 4.3064. Min Act: -0.0000

Data Index: 1160634 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 4.7988. Min Range: -4.7988

Max Act: 4.0454. Min Act: -0.0000

Data Index: 1330869 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.8889. Min Act: -0.0000

Data Index: 634180 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.6896. Min Act: -0.0000

Data Index: 1273500 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.7900. Min Act: -0.0000

Data Index: 5392 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.5153. Min Act: -0.0000

Data Index: 997099 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.7952. Min Act: -0.0000

Data Index: 135974 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.5862. Min Act: -0.0000

Data Index: 1218800 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.7479. Min Act: -0.0000

Data Index: 715074 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.7180. Min Act: -0.0000

Data Index: 595711 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.5787. Min Act: -0.0000

Data Index: 355994 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.3113. Min Act: -0.0000

Data Index: 1145976 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.6102. Min Act: -0.0000

Data Index: 931152 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.2551. Min Act: -0.0000

Data Index: 1059053 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.4200. Min Act: -0.0000

Data Index: 113948 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.4314. Min Act: -0.0000

Data Index: 366279 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.3746. Min Act: -0.0000

Data Index: 736754 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.7988. Min Range: -4.7988

Max Act: 3.3680. Min Act: -0.0000

Data Index: 389959 (C4 (Web Text))

Max Activating Token Index: 268