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

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

Neuron 940 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1267460 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1519048 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0055. Min Act: -0.0002

Data Index: 614604 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0053. Min Act: -0.0002

Data Index: 12004 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0051. Min Act: -0.0002

Data Index: 543994 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0050. Min Act: -0.0003

Data Index: 128083 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1645048 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0051. Min Act: -0.0003

Data Index: 136945 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1225956 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0047. Min Act: -0.0002

Data Index: 584957 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0047. Min Act: -0.0002

Data Index: 969798 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1335502 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0043. Min Act: -0.0002

Data Index: 1218712 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0045. Min Act: -0.0002

Data Index: 121091 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0046. Min Act: -0.0002

Data Index: 1283961 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1175725 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0045. Min Act: -0.0002

Data Index: 1425448 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0044. Min Act: -0.0003

Data Index: 436135 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0044. Min Act: -0.0002

Data Index: 900763 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0045. Min Act: -0.0002

Data Index: 464629 (C4 (Web Text))

Max Activating Token Index: 659