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

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

Neuron 4488 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0046. Min Range: -2.0046

Max Act: 2.0046. Min Act: -0.0000

Data Index: 1048570 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.8629. Min Act: -0.0000

Data Index: 911505 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.9490. Min Act: -0.0000

Data Index: 3179 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1154331 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7757. Min Act: -0.0000

Data Index: 1178060 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.8673. Min Act: -0.0000

Data Index: 691075 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.8496. Min Act: -0.0000

Data Index: 1408225 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7075. Min Act: -0.0000

Data Index: 250381 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7064. Min Act: -0.0000

Data Index: 1235725 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1498023 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1297302 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1240458 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.5874. Min Act: -0.0000

Data Index: 282931 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7066. Min Act: -0.0000

Data Index: 144529 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7601. Min Act: -0.0000

Data Index: 1400805 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.6484. Min Act: -0.0000

Data Index: 530618 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.6281. Min Act: -0.0000

Data Index: 1458352 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1584614 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.6037. Min Act: -0.0000

Data Index: 1632596 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 2.0046. Min Range: -2.0046

Max Act: 1.6018. Min Act: -0.0000

Data Index: 148067 (C4 (Web Text))

Max Activating Token Index: 325