Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 609 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0146. Min Act: -0.0006

Data Index: 349571 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 817965 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1136758 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1264673 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0006

Data Index: 413203 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1096966 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0109. Min Act: -0.0006

Data Index: 954730 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0125. Min Act: -0.0006

Data Index: 863562 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0118. Min Act: -0.0006

Data Index: 199576 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0115. Min Act: -0.0006

Data Index: 34826 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0113. Min Act: -0.0006

Data Index: 408418 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0121. Min Act: -0.0006

Data Index: 415014 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1256703 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0112. Min Act: -0.0006

Data Index: 684290 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1086707 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1338089 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1259052 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0119. Min Act: -0.0006

Data Index: 802200 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0112. Min Act: -0.0006

Data Index: 488991 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0110. Min Act: -0.0006

Data Index: 499978 (C4 (Web Text))

Max Activating Token Index: 913