Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 647 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1317857 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0129. Min Act: -0.0003

Data Index: 540425 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0128. Min Act: -0.0003

Data Index: 299251 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0124. Min Act: -0.0003

Data Index: 715286 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0124. Min Act: -0.0004

Data Index: 393082 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0112. Min Act: -0.0003

Data Index: 547613 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1136118 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0109. Min Act: -0.0003

Data Index: 503339 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0108. Min Act: -0.0003

Data Index: 22745 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0108. Min Act: -0.0003

Data Index: 21115 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0107. Min Act: -0.0003

Data Index: 994416 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0105. Min Act: -0.0004

Data Index: 1191147 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0105. Min Act: -0.0003

Data Index: 282820 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0104. Min Act: -0.0003

Data Index: 729960 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0103. Min Act: -0.0003

Data Index: 263958 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1331951 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1309649 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0102. Min Act: -0.0003

Data Index: 683481 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0102. Min Act: -0.0003

Data Index: 565238 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0102. Min Act: -0.0003

Data Index: 1307632 (C4 (Web Text))

Max Activating Token Index: 399