Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0119. Min Act: -0.0005

Data Index: 113630 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0121. Min Act: -0.0005

Data Index: 78747 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0117. Min Act: -0.0005

Data Index: 17899 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0120. Min Act: -0.0005

Data Index: 81237 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1310021 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0114. Min Act: -0.0005

Data Index: 574073 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0117. Min Act: -0.0005

Data Index: 410950 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1236719 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1126458 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0114. Min Act: -0.0005

Data Index: 650656 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0113. Min Act: -0.0006

Data Index: 291424 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0113. Min Act: -0.0005

Data Index: 477366 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0111. Min Act: -0.0005

Data Index: 368057 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0113. Min Act: -0.0005

Data Index: 604397 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0112. Min Act: -0.0006

Data Index: 466940 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0112. Min Act: -0.0005

Data Index: 394808 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1273748 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0111. Min Act: -0.0005

Data Index: 253262 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1103655 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.0121. Min Range: -0.0121

Max Act: 0.0110. Min Act: -0.0005

Data Index: 189720 (C4 (Web Text))

Max Activating Token Index: 519