Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0000

Data Index: 329835 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0000

Data Index: 86162 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1217085 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0116. Min Act: 0.0000

Data Index: 1356451 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0114. Min Act: -0.0001

Data Index: 585585 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0112. Min Act: -0.0000

Data Index: 76000 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0118. Min Act: -0.0000

Data Index: 336914 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0112. Min Act: -0.0001

Data Index: 856017 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0115. Min Act: -0.0001

Data Index: 236237 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0109. Min Act: -0.0001

Data Index: 247822 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0104. Min Act: -0.0001

Data Index: 885690 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0109. Min Act: -0.0001

Data Index: 335148 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0107. Min Act: -0.0001

Data Index: 917375 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0106. Min Act: -0.0001

Data Index: 948943 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0106. Min Act: -0.0000

Data Index: 194630 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0109. Min Act: -0.0001

Data Index: 1085248 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0105. Min Act: -0.0001

Data Index: 34005 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0104. Min Act: -0.0001

Data Index: 990002 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0108. Min Act: -0.0001

Data Index: 495663 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0103. Min Act: -0.0001

Data Index: 1274777 (C4 (Web Text))

Max Activating Token Index: 142