Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4491 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4068. Min Range: -2.4068

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1516024 (Python Code)

Max Activating Token Index: 602

Text #1

Max Range: 2.4068. Min Range: -2.4068

Max Act: 2.0266. Min Act: -0.0000

Data Index: 1490020 (Python Code)

Max Activating Token Index: 177

Text #2

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.9714. Min Act: -0.0000

Data Index: 1615556 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.9542. Min Act: -0.0000

Data Index: 857736 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.8802. Min Act: -0.0000

Data Index: 1366757 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.8733. Min Act: -0.0000

Data Index: 1596611 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.9062. Min Act: -0.0000

Data Index: 1550070 (Python Code)

Max Activating Token Index: 634

Text #7

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1571456 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.9015. Min Act: -0.0000

Data Index: 1438281 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1546892 (Python Code)

Max Activating Token Index: 987

Text #10

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.9388. Min Act: -0.0000

Data Index: 1543931 (Python Code)

Max Activating Token Index: 244

Text #11

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.5625. Min Act: -0.0000

Data Index: 1620143 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.7473. Min Act: -0.0000

Data Index: 1565359 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.7395. Min Act: -0.0000

Data Index: 119162 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.7093. Min Act: -0.0000

Data Index: 1595037 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.7327. Min Act: -0.0000

Data Index: 1540377 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.5893. Min Act: -0.0000

Data Index: 1577186 (Python Code)

Max Activating Token Index: 948

Text #17

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.5920. Min Act: -0.0000

Data Index: 973699 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1411816 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 2.4068. Min Range: -2.4068

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1532139 (Python Code)

Max Activating Token Index: 697