Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2815 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.7673. Min Act: -0.0000

Data Index: 893217 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6753. Min Act: -0.0001

Data Index: 199822 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1082859 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6872. Min Act: -0.0000

Data Index: 274113 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.7177. Min Act: -0.0001

Data Index: 415177 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6460. Min Act: -0.0001

Data Index: 936719 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6587. Min Act: -0.0000

Data Index: 251070 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6612. Min Act: -0.0000

Data Index: 714242 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6191. Min Act: -0.0000

Data Index: 905347 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6198. Min Act: -0.0000

Data Index: 114610 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1230956 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1056631 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.6138. Min Act: -0.0001

Data Index: 870454 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5647. Min Act: -0.0000

Data Index: 987826 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5742. Min Act: -0.0000

Data Index: 188811 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5535. Min Act: -0.0001

Data Index: 659656 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5665. Min Act: -0.0000

Data Index: 290943 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5646. Min Act: -0.0000

Data Index: 929305 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1313278 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.7673. Min Range: -0.7673

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1320754 (C4 (Web Text))

Max Activating Token Index: 625