Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2979. Min Range: -2.2979

Max Act: 2.2979. Min Act: -0.0001

Data Index: 179657 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.2979. Min Range: -2.2979

Max Act: 2.1009. Min Act: -0.0001

Data Index: 1159300 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.2979. Min Range: -2.2979

Max Act: 2.1563. Min Act: -0.0001

Data Index: 511735 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7432. Min Act: -0.0001

Data Index: 480779 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.8259. Min Act: -0.0000

Data Index: 1301318 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7856. Min Act: -0.0000

Data Index: 1032691 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7885. Min Act: -0.0000

Data Index: 518196 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7696. Min Act: -0.0000

Data Index: 1030251 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7649. Min Act: -0.0000

Data Index: 444004 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6172. Min Act: -0.0001

Data Index: 336494 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7016. Min Act: -0.0000

Data Index: 173348 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1294029 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6930. Min Act: -0.0000

Data Index: 524068 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.5789. Min Act: -0.0000

Data Index: 989103 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6584. Min Act: -0.0000

Data Index: 1017393 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6461. Min Act: -0.0000

Data Index: 1021043 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6311. Min Act: -0.0000

Data Index: 800777 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.5406. Min Act: -0.0000

Data Index: 393389 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1005974 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 2.2979. Min Range: -2.2979

Max Act: 1.6094. Min Act: -0.0000

Data Index: 342754 (C4 (Web Text))

Max Activating Token Index: 808