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

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

Neuron 1608 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.4939. Min Act: -0.0000

Data Index: 90439 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1486678 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1461067 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1533855 (Python Code)

Max Activating Token Index: 841

Text #4

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1615459 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1498575 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1613195 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2972. Min Act: -0.0000

Data Index: 768220 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1099456 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1376648 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1299838 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1473912 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1240293 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1465669 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2709. Min Act: -0.0000

Data Index: 299287 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2608. Min Act: -0.0000

Data Index: 49066 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2967. Min Act: -0.0000

Data Index: 778379 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2361. Min Act: -0.0000

Data Index: 685979 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2551. Min Act: -0.0000

Data Index: 741241 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.4939. Min Range: -0.4939

Max Act: 0.2629. Min Act: -0.0000

Data Index: 320613 (C4 (Web Text))

Max Activating Token Index: 297