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

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

Neuron 2473 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: 0.0955. Min Range: -0.0955

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1090056 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0000

Data Index: 985248 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0930. Min Act: -0.0000

Data Index: 56713 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0834. Min Act: -0.0000

Data Index: 595606 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1614936 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0698. Min Act: -0.0000

Data Index: 245211 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0736. Min Act: -0.0000

Data Index: 259622 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0793. Min Act: -0.0000

Data Index: 566912 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1406810 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0736. Min Act: -0.0000

Data Index: 727445 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0731. Min Act: -0.0000

Data Index: 48407 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1541890 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0714. Min Act: -0.0000

Data Index: 399971 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1614210 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1355615 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1557837 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1500242 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0713. Min Act: -0.0000

Data Index: 708084 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1149216 (C4 (Web Text))

Max Activating Token Index: 123