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

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

Neuron 928 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: 0.0155. Min Range: -0.0155

Max Act: 0.0155. Min Act: -0.0006

Data Index: 787056 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1034134 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0139. Min Act: -0.0006

Data Index: 734564 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0135. Min Act: -0.0006

Data Index: 399085 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0006

Data Index: 79506 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0134. Min Act: -0.0006

Data Index: 235788 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0006

Data Index: 613938 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0006

Data Index: 288102 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0129. Min Act: -0.0006

Data Index: 850873 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1084077 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1265851 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0130. Min Act: -0.0006

Data Index: 236658 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0127. Min Act: -0.0006

Data Index: 460156 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0123. Min Act: -0.0006

Data Index: 133922 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0120. Min Act: -0.0006

Data Index: 580895 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1170540 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0125. Min Act: -0.0006

Data Index: 983108 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1077817 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0126. Min Act: -0.0006

Data Index: 656124 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0155. Min Range: -0.0155

Max Act: 0.0121. Min Act: -0.0006

Data Index: 812986 (C4 (Web Text))

Max Activating Token Index: 900