Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1203763 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1920. Min Act: 0.0000

Data Index: 475377 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1474600 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1536767 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1463519 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1716. Min Act: 0.0003

Data Index: 739099 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1665. Min Act: 0.0003

Data Index: 1212325 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1609. Min Act: -0.0001

Data Index: 428596 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1596. Min Act: -0.0001

Data Index: 556715 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1596. Min Act: -0.0001

Data Index: 117116 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1525. Min Act: -0.0001

Data Index: 217522 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1356533 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1311213 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1502. Min Act: -0.0001

Data Index: 962313 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1491. Min Act: -0.0001

Data Index: 916750 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1450. Min Act: -0.0001

Data Index: 463140 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1407. Min Act: 0.0001

Data Index: 1152651 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1543737 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1193820 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 0.2075. Min Range: -0.2075

Max Act: 0.1402. Min Act: -0.0001

Data Index: 759843 (C4 (Web Text))

Max Activating Token Index: 682