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

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

Neuron 638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0128. Min Act: -0.0006

Data Index: 153770 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1062053 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0006

Data Index: 498973 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0130. Min Act: -0.0006

Data Index: 617582 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1269386 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1170410 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0129. Min Act: -0.0006

Data Index: 117437 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0006

Data Index: 116071 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0127. Min Act: -0.0006

Data Index: 601804 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0006

Data Index: 738790 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0006

Data Index: 549561 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0006

Data Index: 494029 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0006

Data Index: 985246 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1239795 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1216625 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0006

Data Index: 10655 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0006

Data Index: 696999 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0124. Min Act: -0.0006

Data Index: 248413 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0006

Data Index: 878740 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0125. Min Act: -0.0006

Data Index: 772990 (C4 (Web Text))

Max Activating Token Index: 322