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

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

Neuron 4588 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0002

Data Index: 473320 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0113. Min Act: -0.0002

Data Index: 544015 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0112. Min Act: -0.0002

Data Index: 993025 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0110. Min Act: -0.0002

Data Index: 772264 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1601272 (Python Code)

Max Activating Token Index: 221

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0002

Data Index: 796627 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0002

Data Index: 1129038 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1449396 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1528969 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1340233 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0002

Data Index: 413591 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1497703 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 503897 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1057220 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1513124 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1609420 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1052734 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0002

Data Index: 1481348 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1515745 (Python Code)

Max Activating Token Index: 787

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0099. Min Act: -0.0002

Data Index: 1493748 (Python Code)

Max Activating Token Index: 27