Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7660. Min Act: -0.0000

Data Index: 842438 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.7490. Min Act: -0.0000

Data Index: 126139 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6944. Min Act: -0.0000

Data Index: 574727 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1006066 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1014077 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1170494 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6689. Min Act: -0.0000

Data Index: 102112 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1053484 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6400. Min Act: -0.0000

Data Index: 509768 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1175370 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6372. Min Act: -0.0000

Data Index: 735202 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1197985 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6822. Min Act: -0.0000

Data Index: 830351 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6385. Min Act: -0.0000

Data Index: 292884 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1315279 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6158. Min Act: -0.0000

Data Index: 9970 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6538. Min Act: -0.0000

Data Index: 742895 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6116. Min Act: -0.0000

Data Index: 279194 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6236. Min Act: -0.0000

Data Index: 45567 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.7660. Min Range: -0.7660

Max Act: 0.6667. Min Act: -0.0000

Data Index: 772439 (C4 (Web Text))

Max Activating Token Index: 932