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

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

Neuron 141 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.9719. Min Act: -0.0000

Data Index: 1647930 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 7.3780. Min Range: -7.3780

Max Act: 7.0255. Min Act: -0.0000

Data Index: 1509695 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 7.3780. Min Range: -7.3780

Max Act: 7.3780. Min Act: -0.0000

Data Index: 1535808 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.8388. Min Act: -0.0000

Data Index: 102052 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.9690. Min Act: -0.0000

Data Index: 1361111 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 7.3780. Min Range: -7.3780

Max Act: 7.1698. Min Act: -0.0000

Data Index: 1403029 (Python Code)

Max Activating Token Index: 593

Text #6

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.8489. Min Act: -0.0000

Data Index: 788331 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.8701. Min Act: -0.0000

Data Index: 1589620 (Python Code)

Max Activating Token Index: 868

Text #8

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.0842. Min Act: -0.0000

Data Index: 1538089 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 7.3780. Min Range: -7.3780

Max Act: 7.0641. Min Act: -0.0000

Data Index: 1589722 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.6561. Min Act: -0.0000

Data Index: 1565542 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.8161. Min Act: -0.0000

Data Index: 798547 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.5860. Min Act: -0.0000

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.5206. Min Act: -0.0000

Data Index: 1651370 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.2767. Min Act: -0.0000

Data Index: 1386376 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.4799. Min Act: -0.0000

Data Index: 1363943 (Python Code)

Max Activating Token Index: 931

Text #16

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.4726. Min Act: -0.0000

Data Index: 1614639 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.4532. Min Act: -0.0000

Data Index: 1417400 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.4810. Min Act: -0.0000

Data Index: 1469927 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 7.3780. Min Range: -7.3780

Max Act: 6.2326. Min Act: -0.0000

Data Index: 1565615 (Python Code)

Max Activating Token Index: 316