Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0003

Data Index: 400752 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1185126 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0003

Data Index: 807999 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0126. Min Act: -0.0003

Data Index: 807280 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0004

Data Index: 20051 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0123. Min Act: -0.0003

Data Index: 339261 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0003

Data Index: 634206 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1100646 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1035569 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0119. Min Act: -0.0003

Data Index: 694369 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1163058 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0093. Min Act: -0.0003

Data Index: 677162 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1135244 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0099. Min Act: -0.0003

Data Index: 302643 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0004

Data Index: 220493 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0107. Min Act: -0.0003

Data Index: 53621 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1176172 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0095. Min Act: -0.0003

Data Index: 245111 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0085. Min Act: -0.0004

Data Index: 15079 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0103. Min Act: -0.0003

Data Index: 559067 (C4 (Web Text))

Max Activating Token Index: 18