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

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

Neuron 505 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: 0.0149. Min Range: -0.0149

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1025641 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0006

Data Index: 34329 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0144. Min Act: -0.0006

Data Index: 740596 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0143. Min Act: -0.0006

Data Index: 891665 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0141. Min Act: -0.0006

Data Index: 23398 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0141. Min Act: -0.0006

Data Index: 834546 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1330813 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0006

Data Index: 877207 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0128. Min Act: -0.0006

Data Index: 943781 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0130. Min Act: -0.0006

Data Index: 168519 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0125. Min Act: -0.0006

Data Index: 334921 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0127. Min Act: -0.0006

Data Index: 950768 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0119. Min Act: -0.0006

Data Index: 894756 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0124. Min Act: -0.0006

Data Index: 184054 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1257082 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1157506 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0125. Min Act: -0.0006

Data Index: 341129 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1100580 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0121. Min Act: -0.0006

Data Index: 783920 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0121. Min Act: -0.0006

Data Index: 13479 (C4 (Web Text))

Max Activating Token Index: 955