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

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

Neuron 5283 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: 4.0654. Min Range: -4.0654

Max Act: 4.0654. Min Act: 0.0000

Data Index: 1292672 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 4.0654. Min Range: -4.0654

Max Act: 4.0367. Min Act: 0.0000

Data Index: 1184953 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.7951. Min Act: -0.0000

Data Index: 1613388 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.5969. Min Act: -0.0000

Data Index: 18883 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.4632. Min Act: -0.0000

Data Index: 259116 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.3027. Min Act: -0.0000

Data Index: 973447 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.0105. Min Act: -0.0000

Data Index: 259780 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.2314. Min Act: -0.0000

Data Index: 1268369 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.0461. Min Act: -0.0000

Data Index: 706593 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.0400. Min Act: -0.0000

Data Index: 724514 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.8570. Min Act: -0.0000

Data Index: 147699 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.9909. Min Act: -0.0000

Data Index: 74499 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.9595. Min Act: -0.0000

Data Index: 967152 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.9471. Min Act: -0.0000

Data Index: 1058738 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.9531. Min Act: -0.0000

Data Index: 965774 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.0636. Min Act: -0.0000

Data Index: 1097860 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.7496. Min Act: -0.0000

Data Index: 1196939 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.7000. Min Act: -0.0000

Data Index: 1324603 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 4.0654. Min Range: -4.0654

Max Act: 2.8501. Min Act: -0.0000

Data Index: 934631 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 4.0654. Min Range: -4.0654

Max Act: 3.0043. Min Act: -0.0000

Data Index: 398725 (C4 (Web Text))

Max Activating Token Index: 123