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

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

Neuron 926 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3428. Min Act: -0.0001

Data Index: 812037 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3033. Min Act: -0.0001

Data Index: 144471 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1060459 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2730. Min Act: -0.0000

Data Index: 958619 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1180473 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1035774 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1099864 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2700. Min Act: -0.0000

Data Index: 897597 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1289204 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2138. Min Act: -0.0000

Data Index: 584702 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1125443 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2083. Min Act: -0.0000

Data Index: 671523 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2175. Min Act: -0.0000

Data Index: 434489 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1357723 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1222853 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2072. Min Act: -0.0000

Data Index: 437571 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.1946. Min Act: -0.0000

Data Index: 713743 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2300. Min Act: -0.0000

Data Index: 197863 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.2136. Min Act: -0.0001

Data Index: 594048 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.3428. Min Range: -0.3428

Max Act: 0.1962. Min Act: -0.0000

Data Index: 764173 (C4 (Web Text))

Max Activating Token Index: 258