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

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

Neuron 2658 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0003

Data Index: 999929 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1476584 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1394128 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1540464 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0003

Data Index: 450796 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1205092 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0004

Data Index: 673633 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0003

Data Index: 567284 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0004

Data Index: 953860 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1490464 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1179742 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0004

Data Index: 372349 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 723918 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1330069 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0004

Data Index: 1240336 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0004

Data Index: 524083 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1269207 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0004

Data Index: 163504 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1437220 (Python Code)

Max Activating Token Index: 5