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

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

Neuron 228 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: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1376396 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0006

Data Index: 907134 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0005

Data Index: 253397 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0005

Data Index: 745334 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0005

Data Index: 539373 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0005

Data Index: 724585 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1040282 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1628256 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0117. Min Act: -0.0006

Data Index: 896370 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0005

Data Index: 337594 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0005

Data Index: 703080 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0005

Data Index: 167675 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0006

Data Index: 274032 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1364383 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0006

Data Index: 64353 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0005

Data Index: 676796 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1561716 (Python Code)

Max Activating Token Index: 919

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0113. Min Act: -0.0005

Data Index: 974672 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0115. Min Act: -0.0005

Data Index: 870776 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0005

Data Index: 675162 (C4 (Web Text))

Max Activating Token Index: 627