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

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

Neuron 42 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: 0.0157. Min Range: -0.0157

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1317229 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0154. Min Act: -0.0006

Data Index: 700703 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0148. Min Act: -0.0006

Data Index: 630476 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 330761 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0137. Min Act: -0.0006

Data Index: 560546 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0137. Min Act: -0.0006

Data Index: 156531 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 757557 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0133. Min Act: -0.0006

Data Index: 988102 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1296444 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 159686 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1300564 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0130. Min Act: -0.0006

Data Index: 699046 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0139. Min Act: -0.0006

Data Index: 556823 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0006

Data Index: 237000 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0122. Min Act: -0.0006

Data Index: 428190 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1332606 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0108. Min Act: -0.0006

Data Index: 276223 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1119735 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0006

Data Index: 1086975 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1146800 (C4 (Web Text))

Max Activating Token Index: 625