Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1545 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1529504 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0117. Min Act: -0.0006

Data Index: 729170 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0116. Min Act: -0.0006

Data Index: 19591 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0006

Data Index: 801309 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0006

Data Index: 553207 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0006

Data Index: 773830 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1078296 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0110. Min Act: -0.0006

Data Index: 179860 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1548042 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0109. Min Act: -0.0006

Data Index: 905873 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0111. Min Act: -0.0006

Data Index: 675182 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0006

Data Index: 211789 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1191799 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 938931 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1290132 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1417304 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1001784 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1611419 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0101. Min Act: -0.0006

Data Index: 723462 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0126. Min Range: -0.0126

Max Act: 0.0106. Min Act: -0.0006

Data Index: 317290 (C4 (Web Text))

Max Activating Token Index: 870