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

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

Neuron 1043 in Layer 0

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: 1452557 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1579163 (Python Code)

Max Activating Token Index: 702

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1074004 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1616644 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1597816 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1106162 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1045867 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1644950 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0109. Min Act: -0.0006

Data Index: 375837 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1640700 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0111. Min Act: -0.0006

Data Index: 523770 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0108. Min Act: -0.0006

Data Index: 614828 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0106. Min Act: -0.0006

Data Index: 479161 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0107. Min Act: -0.0006

Data Index: 500593 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0106. Min Act: -0.0006

Data Index: 604033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1364200 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0105. Min Act: -0.0006

Data Index: 73063 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0102. Min Act: -0.0005

Data Index: 1544857 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1607948 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1368891 (Python Code)

Max Activating Token Index: 505