Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 542 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3716. Min Act: -0.0001

Data Index: 40295 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3446. Min Act: -0.0001

Data Index: 1085754 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1286338 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1265339 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3179. Min Act: -0.0001

Data Index: 1189194 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3337. Min Act: -0.0001

Data Index: 157834 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1242221 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2887. Min Act: -0.0001

Data Index: 578764 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3055. Min Act: -0.0001

Data Index: 649827 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1103083 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2895. Min Act: -0.0001

Data Index: 187907 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2875. Min Act: -0.0001

Data Index: 938041 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2761. Min Act: -0.0001

Data Index: 1355238 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1349465 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2820. Min Act: -0.0001

Data Index: 732782 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2782. Min Act: -0.0001

Data Index: 186595 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2755. Min Act: -0.0001

Data Index: 576162 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2680. Min Act: -0.0001

Data Index: 122980 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1047839 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.3716. Min Range: -0.3716

Max Act: 0.2636. Min Act: -0.0001

Data Index: 821839 (C4 (Web Text))

Max Activating Token Index: 998