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

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

Neuron 5070 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.7250. Min Act: -0.0000

Data Index: 246160 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.8418. Min Act: -0.0000

Data Index: 806811 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.7748. Min Act: -0.0000

Data Index: 283525 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.6147. Min Act: -0.0000

Data Index: 209077 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.6023. Min Act: -0.0000

Data Index: 357715 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.3343. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.5113. Min Act: -0.0000

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.3240. Min Act: -0.0000

Data Index: 20436 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.3197. Min Act: -0.0000

Data Index: 1058392 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.3992. Min Act: -0.0000

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.3977. Min Act: -0.0000

Data Index: 229989 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.4848. Min Act: -0.0000

Data Index: 179863 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.1372. Min Act: -0.0000

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.0613. Min Act: -0.0000

Data Index: 756275 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.0600. Min Act: -0.0000

Data Index: 641078 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.2345. Min Act: -0.0000

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.5729. Min Act: -0.0000

Data Index: 264461 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.2463. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.2213. Min Act: -0.0000

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 7.8418. Min Range: -7.8418

Max Act: 7.4082. Min Act: -0.0000

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 314