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

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

Neuron 1921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0117. Min Act: -0.0005

Data Index: 263891 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0102. Min Act: -0.0005

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0108. Min Act: -0.0005

Data Index: 199010 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0103. Min Act: -0.0005

Data Index: 343660 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1591247 (Python Code)

Max Activating Token Index: 857

Text #5

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0096. Min Act: -0.0005

Data Index: 1656670 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0113. Min Act: -0.0005

Data Index: 847747 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1334420 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0099. Min Act: -0.0005

Data Index: 1643252 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0102. Min Act: -0.0005

Data Index: 347304 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0107. Min Act: -0.0005

Data Index: 366847 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0105. Min Act: -0.0005

Data Index: 31766 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0105. Min Act: -0.0005

Data Index: 228911 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0101. Min Act: -0.0005

Data Index: 1146570 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0105. Min Act: -0.0005

Data Index: 1225634 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0098. Min Act: -0.0005

Data Index: 387334 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1377487 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0101. Min Act: -0.0005

Data Index: 724073 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1125020 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0117. Min Range: -0.0117

Max Act: 0.0102. Min Act: -0.0005

Data Index: 617710 (C4 (Web Text))

Max Activating Token Index: 797