Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1638406 (Python Code)

Max Activating Token Index: 239

Text #1

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5826. Min Act: 0.0000

Data Index: 1540253 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1371056 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5539. Min Act: 0.0001

Data Index: 1633630 (Python Code)

Max Activating Token Index: 154

Text #4

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5073. Min Act: 0.0000

Data Index: 1647572 (Python Code)

Max Activating Token Index: 650

Text #5

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5036. Min Act: 0.0001

Data Index: 1585726 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.5280. Min Act: 0.0001

Data Index: 1400271 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1578460 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4696. Min Act: 0.0000

Data Index: 1625208 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4722. Min Act: -0.0000

Data Index: 356846 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4537. Min Act: 0.0001

Data Index: 1437464 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4720. Min Act: -0.0000

Data Index: 445468 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4613. Min Act: 0.0001

Data Index: 1386011 (Python Code)

Max Activating Token Index: 544

Text #13

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1520854 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1545186 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4291. Min Act: 0.0000

Data Index: 1517454 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4515. Min Act: 0.0001

Data Index: 1631794 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4508. Min Act: 0.0001

Data Index: 1527235 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.4270. Min Act: -0.0000

Data Index: 42592 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.6787. Min Range: -0.6787

Max Act: 0.3742. Min Act: 0.0000

Data Index: 1540749 (Python Code)

Max Activating Token Index: 671