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

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

Neuron 3152 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: 0.4811. Min Range: -0.4811

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1602218 (Python Code)

Max Activating Token Index: 925

Text #1

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1471551 (Python Code)

Max Activating Token Index: 62

Text #2

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.3083. Min Act: 0.0002

Data Index: 1285399 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2957. Min Act: 0.0002

Data Index: 1484968 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1570658 (Python Code)

Max Activating Token Index: 437

Text #5

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2728. Min Act: 0.0000

Data Index: 1340522 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1550214 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2628. Min Act: 0.0000

Data Index: 1580279 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2810. Min Act: 0.0000

Data Index: 1355127 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1424453 (Python Code)

Max Activating Token Index: 609

Text #10

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1568483 (Python Code)

Max Activating Token Index: 521

Text #11

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2559. Min Act: 0.0000

Data Index: 1409723 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2564. Min Act: 0.0000

Data Index: 402705 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2449. Min Act: 0.0000

Data Index: 1636812 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2291. Min Act: 0.0000

Data Index: 1635552 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1550861 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2597. Min Act: 0.0000

Data Index: 1219496 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1431810 (Python Code)

Max Activating Token Index: 935

Text #18

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2414. Min Act: 0.0000

Data Index: 1381230 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.4811. Min Range: -0.4811

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1471115 (Python Code)

Max Activating Token Index: 555