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

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

Neuron 3488 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.4685. Min Act: -0.0000

Data Index: 982521 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.3282. Min Act: -0.0000

Data Index: 48233 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.3874. Min Act: -0.0000

Data Index: 411180 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.3351. Min Act: -0.0000

Data Index: 888625 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1908. Min Act: -0.0000

Data Index: 8455 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.2160. Min Act: -0.0000

Data Index: 823045 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1127214 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1118478 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1156338 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1060484 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1102743 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1777. Min Act: -0.0000

Data Index: 1198940 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1429. Min Act: -0.0000

Data Index: 968572 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1338. Min Act: -0.0000

Data Index: 57946 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1348610 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1072865 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1618. Min Act: -0.0000

Data Index: 330397 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1258. Min Act: -0.0000

Data Index: 4721 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.1178. Min Act: -0.0000

Data Index: 321489 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.4685. Min Range: -1.4685

Max Act: 1.0812. Min Act: -0.0000

Data Index: 545033 (C4 (Web Text))

Max Activating Token Index: 227