Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 99 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0001

Data Index: 1314273 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0068. Min Act: -0.0001

Data Index: 493890 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0058. Min Act: -0.0001

Data Index: 1321548 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0001

Data Index: 75050 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0067. Min Act: -0.0001

Data Index: 792564 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0063. Min Act: -0.0001

Data Index: 586268 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0042. Min Act: -0.0001

Data Index: 137097 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0066. Min Act: -0.0001

Data Index: 752866 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0064. Min Act: -0.0001

Data Index: 1166449 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0054. Min Act: -0.0001

Data Index: 642367 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0055. Min Act: -0.0001

Data Index: 23321 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0061. Min Act: -0.0001

Data Index: 300809 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0053. Min Act: -0.0001

Data Index: 394342 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0060. Min Act: -0.0001

Data Index: 1257000 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0053. Min Act: -0.0001

Data Index: 818364 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0056. Min Act: -0.0001

Data Index: 482841 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0051. Min Act: -0.0001

Data Index: 670092 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0056. Min Act: -0.0001

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0056. Min Act: -0.0001

Data Index: 201796 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1331111 (C4 (Web Text))

Max Activating Token Index: 952