Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2042 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0004

Data Index: 20608 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0004

Data Index: 922682 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1026941 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1233446 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1137640 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1560564 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 68037 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 204763 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1490049 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 613093 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1153089 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1255429 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 259536 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 517829 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 783694 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0066. Min Act: -0.0004

Data Index: 1083580 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1540706 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 257243 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1585074 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0068. Min Range: -0.0068

Max Act: 0.0065. Min Act: -0.0004

Data Index: 146445 (C4 (Web Text))

Max Activating Token Index: 268