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

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

Neuron 2576 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1915. Min Act: -0.0001

Data Index: 391795 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1613. Min Act: -0.0001

Data Index: 554701 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1112. Min Act: -0.0001

Data Index: 909574 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1085. Min Act: -0.0001

Data Index: 459893 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1138. Min Act: -0.0001

Data Index: 360912 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1049. Min Act: -0.0001

Data Index: 611944 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1077. Min Act: -0.0001

Data Index: 334379 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1247714 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1016. Min Act: -0.0001

Data Index: 78321 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1320541 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1060612 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1338128 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0932. Min Act: -0.0001

Data Index: 568497 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1226598 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0922. Min Act: -0.0002

Data Index: 120527 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0890. Min Act: -0.0001

Data Index: 42756 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0881. Min Act: -0.0001

Data Index: 805701 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1089037 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0946. Min Act: -0.0001

Data Index: 405988 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.0878. Min Act: -0.0001

Data Index: 307679 (C4 (Web Text))

Max Activating Token Index: 317