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

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

Neuron 1145 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0006

Data Index: 191726 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1437350 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1225918 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1463068 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1376148 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0006

Data Index: 953034 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1369540 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1116515 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0006

Data Index: 302386 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0006

Data Index: 159580 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0006

Data Index: 925905 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0087. Min Act: -0.0006

Data Index: 302765 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0100. Min Act: -0.0006

Data Index: 429194 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1600587 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0097. Min Act: -0.0006

Data Index: 281087 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 888054 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1408851 (Python Code)

Max Activating Token Index: 506

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1550952 (Python Code)

Max Activating Token Index: 279

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0006

Data Index: 74846 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0006

Data Index: 467729 (C4 (Web Text))

Max Activating Token Index: 399