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

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

Neuron 1671 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: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 484372 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0006

Data Index: 295279 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0141. Min Act: -0.0006

Data Index: 97869 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1178128 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0006

Data Index: 115764 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0006

Data Index: 942276 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0132. Min Act: -0.0006

Data Index: 258079 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0131. Min Act: -0.0006

Data Index: 385590 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1231192 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0006

Data Index: 846020 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0006

Data Index: 992618 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0006

Data Index: 775679 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0128. Min Act: -0.0006

Data Index: 363250 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1225290 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0006

Data Index: 930977 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0006

Data Index: 942709 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0121. Min Act: -0.0006

Data Index: 88002 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0126. Min Act: -0.0006

Data Index: 537008 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1302473 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0006

Data Index: 228566 (C4 (Web Text))

Max Activating Token Index: 449