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

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

Neuron 3833 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.8893. Min Act: -0.0000

Data Index: 1653738 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.7078. Min Act: -0.0000

Data Index: 1105044 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.6982. Min Act: -0.0000

Data Index: 957620 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.8154. Min Act: -0.0000

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.7072. Min Act: -0.0000

Data Index: 1326502 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.6913. Min Act: -0.0000

Data Index: 855326 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5962. Min Act: -0.0000

Data Index: 1006071 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.6694. Min Act: -0.0000

Data Index: 884594 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1015082 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.7147. Min Act: -0.0000

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.6178. Min Act: -0.0000

Data Index: 1217555 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1392387 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1499371 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1518511 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5373. Min Act: -0.0000

Data Index: 272817 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5794. Min Act: -0.0000

Data Index: 445578 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1479665 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1520997 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1559002 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 1.8893. Min Range: -1.8893

Max Act: 1.4467. Min Act: -0.0000

Data Index: 555257 (C4 (Web Text))

Max Activating Token Index: 916