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

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

Neuron 1273 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3499. Min Range: -1.3499

Max Act: 1.3499. Min Act: -0.0000

Data Index: 1257170 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 1.3499. Min Range: -1.3499

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1582890 (Python Code)

Max Activating Token Index: 487

Text #2

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1601194 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1610324 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1621422 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1479376 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1437336 (Python Code)

Max Activating Token Index: 295

Text #7

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.8046. Min Act: -0.0000

Data Index: 43914 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1442139 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1467850 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7441. Min Act: -0.0000

Data Index: 985600 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1433740 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1040599 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7174. Min Act: 0.0000

Data Index: 960414 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.6991. Min Act: -0.0000

Data Index: 828725 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1270564 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1051871 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1530654 (Python Code)

Max Activating Token Index: 705

Text #18

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1417239 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 1.3499. Min Range: -1.3499

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1116648 (C4 (Web Text))

Max Activating Token Index: 210