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

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

Neuron 6044 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1556847 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1536254 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.9192. Min Act: -0.0000

Data Index: 205455 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.9111. Min Act: 0.0001

Data Index: 1496667 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8530. Min Act: -0.0000

Data Index: 1439766 (Python Code)

Max Activating Token Index: 361

Text #5

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8743. Min Act: -0.0000

Data Index: 196776 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1521537 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8202. Min Act: -0.0000

Data Index: 73705 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8604. Min Act: -0.0000

Data Index: 301282 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1453689 (Python Code)

Max Activating Token Index: 883

Text #10

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.8180. Min Act: -0.0000

Data Index: 766322 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1574540 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1188826 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7462. Min Act: -0.0000

Data Index: 150171 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1061275 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1363364 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1636031 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7384. Min Act: -0.0000

Data Index: 384280 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1583627 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.9766. Min Range: -0.9766

Max Act: 0.7274. Min Act: -0.0000

Data Index: 199751 (C4 (Web Text))

Max Activating Token Index: 770