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

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

Neuron 1653 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: 0.0147. Min Range: -0.0147

Max Act: 0.0147. Min Act: -0.0006

Data Index: 491380 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0138. Min Act: -0.0006

Data Index: 610610 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0129. Min Act: -0.0006

Data Index: 669935 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1106831 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0121. Min Act: -0.0006

Data Index: 35872 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0119. Min Act: -0.0006

Data Index: 514932 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0005

Data Index: 311272 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0120. Min Act: -0.0006

Data Index: 845534 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0114. Min Act: -0.0006

Data Index: 451803 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0113. Min Act: -0.0006

Data Index: 6008 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0112. Min Act: -0.0006

Data Index: 462964 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0112. Min Act: -0.0006

Data Index: 987445 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1300610 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0109. Min Act: -0.0006

Data Index: 507047 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1026590 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0109. Min Act: -0.0006

Data Index: 885246 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0108. Min Act: -0.0005

Data Index: 123466 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0108. Min Act: -0.0005

Data Index: 643996 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0109. Min Act: -0.0006

Data Index: 500586 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0147. Min Range: -0.0147

Max Act: 0.0107. Min Act: -0.0005

Data Index: 735901 (C4 (Web Text))

Max Activating Token Index: 957