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

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

Neuron 150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0006

Data Index: 685429 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1254998 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0074. Min Act: -0.0006

Data Index: 825225 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0066. Min Act: -0.0006

Data Index: 274647 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0066. Min Act: -0.0006

Data Index: 741336 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1259013 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0065. Min Act: -0.0006

Data Index: 7989 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1387541 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0065. Min Act: -0.0006

Data Index: 476383 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0064. Min Act: -0.0006

Data Index: 1385645 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0063. Min Act: -0.0006

Data Index: 725452 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0064. Min Act: -0.0006

Data Index: 531015 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0061. Min Act: -0.0006

Data Index: 368365 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0060. Min Act: -0.0006

Data Index: 405298 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0061. Min Act: -0.0006

Data Index: 409977 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1000170 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0063. Min Act: -0.0006

Data Index: 101231 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0060. Min Act: -0.0006

Data Index: 99435 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0059. Min Act: -0.0006

Data Index: 203139 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0063. Min Act: -0.0006

Data Index: 184811 (C4 (Web Text))

Max Activating Token Index: 70