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

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

Neuron 1533 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: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0006

Data Index: 936414 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0117. Min Act: -0.0006

Data Index: 2648 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0113. Min Act: -0.0006

Data Index: 660071 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1153931 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1454092 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0100. Min Act: -0.0006

Data Index: 352977 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0099. Min Act: -0.0006

Data Index: 828127 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0101. Min Act: -0.0006

Data Index: 705704 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0098. Min Act: -0.0006

Data Index: 250501 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0098. Min Act: -0.0005

Data Index: 1255827 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0096. Min Act: -0.0006

Data Index: 903331 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1285568 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0095. Min Act: -0.0006

Data Index: 131396 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0094. Min Act: -0.0006

Data Index: 511721 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1352297 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1162290 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0092. Min Act: -0.0006

Data Index: 724158 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1535988 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0089. Min Act: -0.0006

Data Index: 901084 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1047517 (C4 (Web Text))

Max Activating Token Index: 771