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

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

Neuron 5795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1581290 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.3907. Min Act: -0.0000

Data Index: 949194 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1604363 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.2756. Min Act: -0.0000

Data Index: 849177 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.2538. Min Act: -0.0000

Data Index: 1401705 (Python Code)

Max Activating Token Index: 159

Text #5

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1999. Min Act: -0.0000

Data Index: 1604530 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1505821 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1867. Min Act: -0.0000

Data Index: 706642 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1356. Min Act: -0.0000

Data Index: 436781 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1743. Min Act: -0.0000

Data Index: 1178820 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1394. Min Act: -0.0000

Data Index: 655491 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1659. Min Act: -0.0000

Data Index: 41798 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1221718 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0697. Min Act: -0.0000

Data Index: 128390 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1296. Min Act: -0.0000

Data Index: 905240 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1394980 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1175993 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1442615 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0514. Min Act: -0.0000

Data Index: 856095 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1043. Min Act: -0.0000

Data Index: 1653901 (Python Code)

Max Activating Token Index: 860