Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1067 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0006

Data Index: 885034 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1192628 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0063. Min Act: -0.0006

Data Index: 219130 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0059. Min Act: -0.0006

Data Index: 361058 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0057. Min Act: -0.0006

Data Index: 620374 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1289664 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0058. Min Act: -0.0006

Data Index: 160987 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0006

Data Index: 934837 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1487531 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1584727 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0056. Min Act: -0.0006

Data Index: 674657 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1448684 (Python Code)

Max Activating Token Index: 538

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0006

Data Index: 336975 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0006

Data Index: 380169 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1633008 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1343885 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0054. Min Act: -0.0006

Data Index: 499989 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1444915 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0006

Data Index: 723763 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0053. Min Act: -0.0006

Data Index: 844856 (C4 (Web Text))

Max Activating Token Index: 719