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

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

Neuron 3901 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5004. Min Range: -3.5004

Max Act: 3.5004. Min Act: -0.0000

Data Index: 1005135 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 3.5004. Min Range: -3.5004

Max Act: 3.3564. Min Act: -0.0000

Data Index: 1417773 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 3.5004. Min Range: -3.5004

Max Act: 3.0305. Min Act: -0.0000

Data Index: 217186 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 3.5004. Min Range: -3.5004

Max Act: 3.0001. Min Act: 0.0000

Data Index: 635776 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.6546. Min Act: -0.0000

Data Index: 208527 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.5004. Min Range: -3.5004

Max Act: 3.0053. Min Act: 0.0000

Data Index: 925218 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.6487. Min Act: -0.0000

Data Index: 881737 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.6675. Min Act: -0.0000

Data Index: 587814 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.4500. Min Act: 0.0000

Data Index: 597991 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.4422. Min Act: -0.0000

Data Index: 473797 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.4592. Min Act: -0.0000

Data Index: 1203151 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.1862. Min Act: 0.0000

Data Index: 127711 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.1338. Min Act: 0.0000

Data Index: 379129 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.1415. Min Act: -0.0000

Data Index: 1216655 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.2216. Min Act: -0.0000

Data Index: 923630 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.3004. Min Act: -0.0000

Data Index: 951471 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.0620. Min Act: 0.0000

Data Index: 783333 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.0438. Min Act: -0.0000

Data Index: 184032 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.1021. Min Act: -0.0000

Data Index: 997408 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 3.5004. Min Range: -3.5004

Max Act: 2.0524. Min Act: -0.0000

Data Index: 1286748 (C4 (Web Text))

Max Activating Token Index: 923