Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0002

Data Index: 501222 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0124. Min Act: -0.0002

Data Index: 558495 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1278948 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0123. Min Act: -0.0003

Data Index: 524527 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 811921 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0003

Data Index: 163423 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0003

Data Index: 963053 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1042606 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0002

Data Index: 133239 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0003

Data Index: 280875 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0003

Data Index: 85539 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0002

Data Index: 990474 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 459610 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0108. Min Act: -0.0003

Data Index: 899011 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0003

Data Index: 581331 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0107. Min Act: -0.0003

Data Index: 769382 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1098123 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1218629 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0109. Min Act: -0.0002

Data Index: 203952 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0105. Min Act: -0.0003

Data Index: 510947 (C4 (Web Text))

Max Activating Token Index: 123