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

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

Neuron 351 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: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0004

Data Index: 812952 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0110. Min Act: -0.0004

Data Index: 202840 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0004

Data Index: 504439 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0109. Min Act: -0.0004

Data Index: 1455907 (Python Code)

Max Activating Token Index: 895

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0004

Data Index: 1092282 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0108. Min Act: -0.0004

Data Index: 1356919 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0107. Min Act: -0.0004

Data Index: 86533 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0107. Min Act: -0.0004

Data Index: 1624777 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0107. Min Act: -0.0004

Data Index: 275200 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0106. Min Act: -0.0004

Data Index: 303620 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0106. Min Act: -0.0004

Data Index: 1329555 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1440741 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 456867 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0004

Data Index: 471531 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 816395 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 774897 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1235769 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0004

Data Index: 902912 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0004

Data Index: 989935 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0104. Min Act: -0.0004

Data Index: 193844 (C4 (Web Text))

Max Activating Token Index: 242