Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 848 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0106. Min Act: -0.0001

Data Index: 1333242 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0001

Data Index: 214863 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0001

Data Index: 763129 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0103. Min Act: -0.0001

Data Index: 385841 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0105. Min Act: -0.0001

Data Index: 174279 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0103. Min Act: -0.0001

Data Index: 1045280 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0101. Min Act: -0.0001

Data Index: 606253 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0101. Min Act: -0.0001

Data Index: 1162435 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0102. Min Act: -0.0001

Data Index: 390416 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0100. Min Act: -0.0001

Data Index: 113540 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0102. Min Act: -0.0001

Data Index: 76683 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0001

Data Index: 481310 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0098. Min Act: -0.0001

Data Index: 553928 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0001

Data Index: 1167280 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0001

Data Index: 530706 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0001

Data Index: 1092737 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0001

Data Index: 1075221 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0001

Data Index: 1297672 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0001

Data Index: 899949 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0001

Data Index: 528860 (C4 (Web Text))

Max Activating Token Index: 100