Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2766 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.0423. Min Range: -3.0423

Max Act: 3.0423. Min Act: -0.0001

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.9583. Min Act: -0.0001

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.8370. Min Act: -0.0000

Data Index: 299324 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.7049. Min Act: -0.0000

Data Index: 1634673 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.5464. Min Act: -0.0001

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2856. Min Act: -0.0000

Data Index: 655633 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2999. Min Act: -0.0001

Data Index: 1512148 (Python Code)

Max Activating Token Index: 356

Text #7

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1854. Min Act: -0.0000

Data Index: 638758 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1325. Min Act: -0.0001

Data Index: 1501800 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1398. Min Act: -0.0000

Data Index: 1466422 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1990. Min Act: -0.0000

Data Index: 1302177 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0413. Min Act: -0.0000

Data Index: 1637393 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1010. Min Act: -0.0001

Data Index: 1258670 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.2098. Min Act: -0.0001

Data Index: 1455642 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0323. Min Act: -0.0000

Data Index: 1609867 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.1745. Min Act: -0.0000

Data Index: 758655 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0965. Min Act: -0.0000

Data Index: 338204 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0219. Min Act: -0.0000

Data Index: 270279 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.0423. Min Range: -3.0423

Max Act: 2.0639. Min Act: -0.0000

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 1007