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

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

Neuron 962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2726. Min Range: -7.2726

Max Act: 7.2726. Min Act: -0.0001

Data Index: 1643779 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 7.2726. Min Range: -7.2726

Max Act: 5.2219. Min Act: -0.0002

Data Index: 1423316 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 7.2726. Min Range: -7.2726

Max Act: 4.7839. Min Act: -0.0002

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #3

Max Range: 7.2726. Min Range: -7.2726

Max Act: 4.4754. Min Act: -0.0002

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.7168. Min Act: -0.0002

Data Index: 1601652 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.6026. Min Act: -0.0002

Data Index: 1641948 (Python Code)

Max Activating Token Index: 400

Text #6

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.4078. Min Act: -0.0002

Data Index: 1439139 (Python Code)

Max Activating Token Index: 990

Text #7

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.1323. Min Act: -0.0001

Data Index: 1438075 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.1827. Min Act: -0.0001

Data Index: 1594968 (Python Code)

Max Activating Token Index: 660

Text #9

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.1082. Min Act: -0.0002

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.0331. Min Act: -0.0002

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 7.2726. Min Range: -7.2726

Max Act: 3.1598. Min Act: -0.0002

Data Index: 1377033 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.9991. Min Act: -0.0002

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.9109. Min Act: -0.0002

Data Index: 1655744 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.8922. Min Act: -0.0002

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.7351. Min Act: -0.0001

Data Index: 1562798 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.7142. Min Act: -0.0002

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.7330. Min Act: -0.0001

Data Index: 1360562 (Python Code)

Max Activating Token Index: 619

Text #18

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.5722. Min Act: -0.0001

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 7.2726. Min Range: -7.2726

Max Act: 2.5475. Min Act: -0.0001

Data Index: 1622014 (Python Code)

Max Activating Token Index: 753